© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10561
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" and variations of its usage, often indicating the existence or presence of something

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

    the word "there" at the beginning of clauses or sentences.

    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
     SqlCommand
    -0.47
    lacian
    -0.47
     betweenstory
    -0.46
     setEmail
    -0.45
    enumii
    -0.45
    Personendaten
    -0.44
     WaitForSeconds
    -0.43
    atians
    -0.43
     ujednoznacz
    -0.42
    典
    -0.42
    POSITIVE LOGITS
     are
    0.54
     is
    0.51
    ьаж
    0.50
     exist
    0.40
     zijn
    0.38
     ARE
    0.36
     exists
    0.36
     were
    0.35
    AutoScaleMode
    0.34
    以來
    0.34
    Activations Density 0.160%

    No Known Activations