© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10080
    Prev
    Next
    INDEX
    Explanations

    words indicating a significant quantity or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.85
     发表于
    -0.84
     HttpHeaders
    -0.84
    principalColumn
    -0.81
    ioutil
    -0.80
    |}{$
    -0.71
     khuẩn
    -0.70
    owulf
    -0.70
    +#+#
    -0.69
    WriteBarrier
    -0.69
    POSITIVE LOGITS
     much
    2.66
    much
    2.52
    Much
    2.31
     Much
    2.30
     MUCH
    2.06
     mucho
    1.83
     beaucoup
    1.60
    mucho
    1.49
     viel
    1.48
     mycket
    1.37
    Activations Density 0.176%

    No Known Activations