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. 17-GEMMASCOPE-RES-16K
    6. 1084
    Prev
    Next
    INDEX
    Explanations

    the opening of a text or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amado
    -0.59
     AspNetCore
    -0.59
     diamants
    -0.55
     inova
    -0.55
     Sexy
    -0.54
     précé
    -0.54
     wrongs
    -0.53
     normalization
    -0.52
    extré
    -0.51
     vroe
    -0.51
    POSITIVE LOGITS
     AssemblyTitle
    0.68
    AlterField
    0.65
    IsMutable
    0.62
     GenerationType
    0.60
    <bos>
    0.59
    하다
    0.58
    énario
    0.58
    Παραπομπές
    0.57
     hwnd
    0.57
     كومونز
    0.55
    Activations Density 0.137%

    No Known Activations