© 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 - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 48
    Prev
    Next
    INDEX
    Explanations

    insights related to discussions or opinions about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.93
     EconPapers
    -0.89
     propOrder
    -0.84
    AutoScaleMode
    -0.83
    withIdentifier
    -0.83
    featureID
    -0.80
    Попис
    -0.79
    complexContent
    -0.77
    WebElementEntity
    -0.76
    TargetException
    -0.74
    POSITIVE LOGITS
     it
    0.59
    Especially
    0.58
     happening
    0.56
     Happening
    0.56
     especially
    0.56
    它
    0.52
     Especially
    0.52
    it
    0.52
    It
    0.51
     anyone
    0.49
    Activations Density 0.377%

    No Known Activations