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. 12077
    Prev
    Next
    INDEX
    Explanations

    references to specific physical locations or coordinates

    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
    PrototypeOf
    -0.56
     Gutierrez
    -0.53
    ISupport
    -0.53
    diger
    -0.52
    uel
    -0.52
     betweenstory
    -0.52
     besch
    -0.51
     intest
    -0.50
    hm
    -0.49
    مش
    -0.49
    POSITIVE LOGITS
    AnchorStyles
    0.73
    HtmlAttribute
    0.71
    AxisAlignment
    0.70
     cavallo
    0.69
     Ankunft
    0.69
     atteinte
    0.69
     eût
    0.66
     Lorsqu
    0.65
     arrivals
    0.65
     resourceCulture
    0.63
    Activations Density 0.391%

    No Known Activations