© 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. 12-GEMMASCOPE-RES-16K
    6. 16174
    Prev
    Next
    INDEX
    Explanations

    mentions of biological or physiological responses related to human perception and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.64
    WithIOException
    -0.59
     Gazetteer
    -0.55
    ostante
    -0.55
     telefonisch
    -0.55
    pegno
    -0.53
     hendes
    -0.52
    GeneratedCode
    -0.52
    yntaxException
    -0.52
    mybatisplus
    -0.52
    POSITIVE LOGITS
     psychological
    0.56
     human
    0.55
     subconsciously
    0.54
     natural
    0.54
     psychologically
    0.53
     people
    0.51
    didSet
    0.49
    natural
    0.48
     humans
    0.47
    Trusted
    0.47
    Activations Density 0.352%

    No Known Activations