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. 2-GEMMASCOPE-RES-16K
    6. 14786
    Prev
    Next
    INDEX
    Explanations

    references to perspectives and points of view

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usermodel
    -0.76
    èlement
    -0.65
    lamabad
    -0.65
     GoogleFonts
    -0.64
     /\.(
    -0.64
     נה
    -0.64
    ็จ
    -0.60
    äfts
    -0.59
     Walkover
    -0.59
     requestCode
    -0.58
    POSITIVE LOGITS
     perspective
    3.37
     Perspective
    2.99
     perspectives
    2.92
    perspective
    2.78
    Perspective
    2.69
     PERSPECT
    2.64
     Perspectives
    2.36
     perspec
    2.29
     perspectiva
    2.25
    Perspectives
    2.16
    Activations Density 0.074%

    No Known Activations