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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2736
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 's' in various contexts

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

    possessive forms of singular nouns or pronouns (indicated by 's).

    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
    awtextra
    -0.65
     defaultstate
    -0.57
    GOTREF
    -0.52
    原始内容存档于
    -0.51
     otomatig
    -0.50
     فريبيس
    -0.48
    aarrggbb
    -0.45
     وتسجيلات
    -0.45
    ReusableCell
    -0.44
     صوتيه
    -0.44
    POSITIVE LOGITS
     own
    1.01
     latest
    0.68
     entire
    0.63
     biggest
    0.63
     newest
    0.63
     ability
    0.62
     respective
    0.60
     egne
    0.59
     Own
    0.56
    s
    0.56
    Activations Density 0.229%

    No Known Activations