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. 11-GEMMASCOPE-RES-16K
    6. 14149
    Prev
    Next
    INDEX
    Explanations

    specialized terminologies related to data structure definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.85
     Theſe
    -0.78
     Efq
    -0.77
    BeginContext
    -0.70
    EndContext
    -0.69
     CreateTagHelper
    -0.68
    الحياه
    -0.63
    enumi
    -0.62
    Referències
    -0.60
     poffe
    -0.59
    POSITIVE LOGITS
     kasarigan
    0.66
    </u>
    0.56
    findpost
    0.56
    </h5>
    0.55
    ksessa
    0.55
    </i>
    0.54
    tahankan
    0.52
     ProtoMessage
    0.51
     Doodle
    0.48
     finnas
    0.48
    Activations Density 0.038%

    No Known Activations