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. 5452
    Prev
    Next
    INDEX
    Explanations

    conversations involving personal exchanges and sharing of contact information

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

    Quoted speech introductions

    np_acts-logits-general · gemini-2.0-flash

    dialogue transitions

    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
    ↵↵
    -0.53
     $
    -0.48
    ry
    -0.42
     general
    -0.42
    ;
    -0.41
     the
    -0.40
    #
    -0.38
    ↵
    -0.38
     
    -0.38
    pas
    -0.37
    POSITIVE LOGITS
    цездатний
    1.03
    Билгалдахарш
    1.01
    IntoConstraints
    0.85
     المعيارى
    0.84
    StoryboardSegue
    0.83
    DockStyle
    0.79
     Мексичка
    0.78
    دانشنامهٔ
    0.78
    NUMX
    0.77
     myſelf
    0.76
    Activations Density 0.106%

    No Known Activations