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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6640
    Prev
    Next
    INDEX
    Explanations

    instances of exceptionally strong numerical values or specific key numeric outputs in a document

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

    Follows certain months or brands

    np_acts-logits-general · gemini-2.0-flash

    affirmative confirmations

    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
    ----</
    -0.63
    .},
    -0.63
    NUMX
    -0.60
    ={`/
    -0.58
    ."));
    -0.57
    Filmo
    -0.55
    $_['
    -0.55
    bkz
    -0.55
    });*/
    -0.54
    fromCharCode
    -0.54
    POSITIVE LOGITS
     Oh
    0.89
    Oh
    0.85
     OK
    0.83
     Okay
    0.81
    OK
    0.80
     alright
    0.79
     yes
    0.79
     oh
    0.78
    Okay
    0.76
     okay
    0.76
    Activations Density 0.215%

    No Known Activations