© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    statements regarding the existence or state of entities or conditions

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

    the verb "is" and its variations in predicative or descriptive statements.

    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
    :✨
    -0.54
    RegressionTest
    -0.41
    Introduced
    -0.37
    ViewFeatures
    -0.36
    EGL
    -0.33
     IFTT
    -0.33
    ALF
    -0.32
    <?
    -0.32
    ADL
    -0.31
    ContentAlignment
    -0.31
    POSITIVE LOGITS
     becoming
    1.34
     being
    1.23
     getting
    1.12
     causing
    1.09
     proving
    1.04
     making
    1.01
     taking
    1.01
    becoming
    1.00
     behaving
    1.00
     gaining
    0.98
    Activations Density 0.521%

    No Known Activations