© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 871
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatment effectiveness and variability

    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
    WebVitals
    -0.55
     FetchType
    -0.49
     transfieras
    -0.48
    ئيس
    -0.46
    requireNonNull
    -0.45
     AssemblyVersion
    -0.45
    GraphicsUnit
    -0.44
     المعيارى
    -0.44
    AutoScale
    -0.43
    よいよ
    -0.43
    POSITIVE LOGITS
     interrupted
    1.09
     hampered
    1.08
     hindered
    0.98
     marred
    0.92
     thwarted
    0.92
     impeded
    0.85
     bị
    0.83
    interrupted
    0.82
     blocked
    0.80
     disrupted
    0.79
    Activations Density 0.398%

    No Known Activations