© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11151
    Prev
    Next
    INDEX
    Explanations

    references to specific educational institutions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordat
    -0.56
    sessionId
    -0.48
    DEVICES
    -0.46
    internalType
    -0.46
    wnież
    -0.45
     stade
    -0.45
    หน้านี้
    -0.44
    ydney
    -0.44
    ToBounds
    -0.44
    xFFFFFF
    -0.44
    POSITIVE LOGITS
    ฯ
    0.72
    gebob
    0.49
    usercontent
    0.42
    RenderAtEndOf
    0.42
    flashdata
    0.41
     disambiguazione
    0.41
    bcryptjs
    0.41
    __":
    
    0.40
    })->
    0.40
    UrlResolution
    0.39
    Activations Density 1.376%

    No Known Activations