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. 20-GEMMASCOPE-RES-16K
    6. 16335
    Prev
    Next
    INDEX
    Explanations

    references to physical confrontation and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "beat" and its variations

    np_acts-logits-general · gemini-2.0-flash

    beat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YLON
    -0.52
    EndContext
    -0.51
     sociaux
    -0.50
     Qaraldi
    -0.49
    vertreter
    -0.48
     مرئيه
    -0.48
    Py
    -0.48
    Coy
    -0.47
     xã
    -0.47
    nungs
    -0.45
    POSITIVE LOGITS
     BEAT
    1.44
     beat
    1.37
     beats
    1.36
     Beat
    1.32
     beating
    1.24
    BEAT
    1.23
     Beats
    1.23
    Beat
    1.18
    beat
    1.18
    Beats
    1.12
    Activations Density 0.070%

    No Known Activations