© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1626
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron activates for phrases that begin with "On the other hand" and similar transitional phrases that introduce contrasting information in academic or mathematical text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the phrase "On the other hand" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused43>
    -1.36
    <unused74>
    -1.35
    <pad>
    -1.35
    <unused51>
    -1.35
    <unused23>
    -1.34
    <unused14>
    -1.34
    <unused41>
    -1.34
    <unused42>
    -1.34
    [@BOS@]
    -1.34
    <unused8>
    -1.34
    POSITIVE LOGITS
     recogida
    0.30
     dignidad
    0.27
     enseñ
    0.25
     vuestra
    0.25
     yapıl
    0.25
     très
    0.24
     oscuridad
    0.24
    <em>
    0.24
     automáticamente
    0.24
     preferido
    0.24
    Activations Density 2.123%

    No Known Activations