© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15700
    Prev
    Next
    INDEX
    Explanations

    function calls related to network actions and handling responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agger
    -0.46
     žaid
    -0.45
     Silvio
    -0.44
    processable
    -0.44
    PrototypeOf
    -0.44
    alista
    -0.43
     indebted
    -0.41
     modernity
    -0.40
    ợ
    -0.40
    timestamps
    -0.40
    POSITIVE LOGITS
    expandindo
    0.86
     CreateTagHelper
    0.76
     resourceCulture
    0.68
     بيها
    0.65
    nonatomic
    0.64
    tvguidetime
    0.64
     unknownFields
    0.63
    RTLR
    0.63
    CppMethod
    0.62
    UserScript
    0.62
    Activations Density 0.621%

    No Known Activations