© 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. 1906
    Prev
    Next
    INDEX
    Explanations

    repetitive uses of the pronoun "it"

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

    the pronoun "it" used as a subject in 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
     enjoyed
    -0.47
    bitField
    -0.44
     msglen
    -0.44
    ソッド
    -0.43
    GHIJKLM
    -0.39
     surla
    -0.39
    SharedCtor
    -0.38
    省市镇
    -0.37
    jenner
    -0.36
     schuldig
    -0.35
    POSITIVE LOGITS
     happen
    0.58
     happened
    0.57
     happens
    0.54
     hurts
    0.53
     happening
    0.53
    happened
    0.49
     terjadi
    0.49
    exitRule
    0.49
    Personensuche
    0.48
     rained
    0.48
    Activations Density 0.248%

    No Known Activations