Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12552
    Prev
    Next
    INDEX
    Explanations

    terms related to impact and its effects on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vettore
    -0.49
    segu
    -0.47
    biskan
    -0.47
    runde
    -0.46
    imbang
    -0.45
     raccol
    -0.44
     mengumpulkan
    -0.44
    闪过
    -0.44
    sco
    -0.44
     certaines
    -0.44
    POSITIVE LOGITS
     affecting
    1.15
     impacting
    1.14
     affects
    1.08
     impacted
    1.06
     affect
    1.04
     impacts
    1.03
     Affects
    1.01
     AFFECT
    1.01
     Affecting
    0.96
     impact
    0.96
    Activations Density 0.536%

    No Known Activations