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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3165
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to purchasing and using products

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

    Following a verb of purchase or inclusion

    np_acts-logits-general · gemini-2.0-flash

    purchase and consumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.71
    InputBorder
    -0.64
    יצד
    -0.63
    extAlignment
    -0.62
     يتيمه
    -0.62
     محفوظة
    -0.60
    AnchorStyles
    -0.60
    ГЛА
    -0.58
    protoimpl
    -0.58
    SourceChecksum
    -0.58
    POSITIVE LOGITS
     it
    0.66
     them
    0.57
     earlier
    0.56
    annya
    0.56
     asta
    0.55
     yesterday
    0.54
     esso
    0.53
     akkor
    0.52
     later
    0.51
     him
    0.51
    Activations Density 0.360%

    No Known Activations