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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9624
    Prev
    Next
    INDEX
    Explanations

    expressions of shock and emotional responses in intense or violent situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.83
     समीक्षाओं
    -0.80
    ſelves
    -0.80
    YourGuide
    -0.80
    Архівовано
    -0.78
    _();
    -0.73
     pleaſure
    -0.73
    OGND
    -0.71
    ſelf
    -0.71
     estekak
    -0.71
    POSITIVE LOGITS
    nonatomic
    0.52
    TextWatcher
    0.51
     blinked
    0.51
     smile
    0.51
    stateParams
    0.50
    ↵↵
    0.49
     shivered
    0.48
     trembled
    0.48
     StringTokenizer
    0.46
     faint
    0.44
    Activations Density 0.430%

    No Known Activations