© 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. 21-GEMMASCOPE-RES-16K
    6. 10969
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "impact" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zijne
    -0.44
    ◘
    -0.38
    Doctor
    -0.38
     useRef
    -0.38
     BoxDecoration
    -0.38
    addButton
    -0.37
     Normdatei
    -0.37
     getRule
    -0.37
    WebServlet
    -0.37
    scre
    -0.36
    POSITIVE LOGITS
     IMPACT
    0.98
    Impact
    0.92
     Impact
    0.91
    IMPACT
    0.84
     impact
    0.80
    impact
    0.77
    Impacts
    0.75
     impacto
    0.75
     impacting
    0.73
     Impacts
    0.73
    Activations Density 0.130%

    No Known Activations