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. 19-GEMMASCOPE-RES-16K
    6. 1860
    Prev
    Next
    INDEX
    Explanations

    references to programming and coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.96
    GraphicsUnit
    -0.80
    Diweddarwch
    -0.76
    fromnode
    -0.74
     himo
    -0.68
    Portale
    -0.68
    ArgsConstructor
    -0.65
    WindowConstants
    -0.65
    NameInMap
    -0.64
     OnInit
    -0.63
    POSITIVE LOGITS
     Sp
    1.70
    Sp
    1.64
     spec
    1.61
     SP
    1.60
     sp
    1.53
    SP
    1.53
     Spec
    1.50
    sp
    1.49
     Spe
    1.46
    Spec
    1.46
    Activations Density 0.149%

    No Known Activations