Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14205
    Prev
    Next
    INDEX
    Explanations

    expressions of personal qualifications and emotional states

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

    I am so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.58
    UrlResolution
    -0.50
    ValueStyle
    -0.47
     itſelf
    -0.47
     précé
    -0.46
     répondit
    -0.46
     conmigo
    -0.45
     répondu
    -0.44
     prédio
    -0.44
     typique
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.59
    __*/
    0.53
    complexContent
    0.51
     want
    0.46
     Мексичка
    0.46
    ReusableCell
    0.46
    MultipartFile
    0.46
    GEBURTSDATUM
    0.45
    limus
    0.45
    ConstraintMaker
    0.44
    Activations Density 0.036%

    No Known Activations