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. 2898
    Prev
    Next
    INDEX
    Explanations

    corporate entities and their activities

    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
    routeProvider
    -0.75
    ThroughAttribute
    -0.55
    NetworkInfo
    -0.54
    Hochspringen
    -0.53
     wireType
    -0.53
    afone
    -0.53
    вица
    -0.52
    PullParser
    -0.51
    tagHelperRunner
    -0.50
    GIH
    -0.50
    POSITIVE LOGITS
     leading
    0.73
     headquartered
    0.71
    Datuak
    0.69
     provider
    0.67
     specializing
    0.65
    leading
    0.64
     specialized
    0.63
     specialising
    0.63
     specializes
    0.62
     providing
    0.61
    Activations Density 0.179%

    No Known Activations