© 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. 12840
    Prev
    Next
    INDEX
    Explanations

    references to responsibility and positive impact

    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
    évaluateur
    -0.76
    +#+#
    -0.70
    LookAnd
    -0.67
    IntoConstraints
    -0.60
    setVerticalGroup
    -0.59
     Taktlose
    -0.58
    енча
    -0.57
    webElementXpaths
    -0.55
     <=",
    -0.55
     Theſe
    -0.53
    POSITIVE LOGITS
     impact
    1.70
    impact
    1.46
     Impact
    1.44
    Impact
    1.37
     influence
    1.23
     impacts
    1.18
     effect
    1.17
     impactful
    1.16
     impacto
    1.12
     impacting
    1.10
    Activations Density 0.236%

    No Known Activations