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. 4-GEMMASCOPE-RES-16K
    6. 3155
    Prev
    Next
    INDEX
    Explanations

    citations and references within legal texts

    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
    StreetMap
    -0.74
    sizeCache
    -0.65
    UnusedPrivate
    -0.65
    bootstrapcdn
    -0.63
    Personensuche
    -0.61
    exitRule
    -0.59
     himo
    -0.59
     ***!
    -0.57
    Koordinaten
    -0.56
    tagHelperRunner
    -0.56
    POSITIVE LOGITS
    Cyfeiriadau
    0.57
     //$
    0.56
    Hentet
    0.55
     noqa
    0.53
     hâte
    0.53
     Ibid
    0.53
     AppModule
    0.53
    verture
    0.51
    ài
    0.51
    lapsingToolbar
    0.50
    Activations Density 1.745%

    No Known Activations