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. 14-GEMMASCOPE-RES-16K
    6. 3055
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and navigation elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.84
     ModelExpression
    -0.83
    AndEndTag
    -0.82
     propOrder
    -0.82
    ')}}">
    -0.80
    fjspx
    -0.77
    setVerticalGroup
    -0.76
    principalTable
    -0.75
    endregion
    -0.73
     referrerpolicy
    -0.73
    POSITIVE LOGITS
    </h5>
    0.49
     जगह
    0.46
    ontale
    0.45
     ţ
    0.45
     lyre
    0.44
    бочка
    0.44
     '*')
    0.43
    "]();
    0.43
    --
    0.43
     Dordrecht
    0.42
    Activations Density 0.144%

    No Known Activations