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. 5-GEMMASCOPE-RES-16K
    6. 11204
    Prev
    Next
    INDEX
    Explanations

    references to musical groups or bands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̷
    -0.88
    rences
    -0.86
    حياتها
    -0.79
    jectives
    -0.76
    ureka
    -0.75
     Vern
    -0.75
    ])));
    -0.74
    >]
    -0.71
    //});
    -0.71
     verg
    -0.71
    POSITIVE LOGITS
     bands
    2.47
     band
    2.41
    Band
    2.39
     BAND
    2.38
     Band
    2.32
    band
    2.24
     Bands
    2.24
    BAND
    2.15
    bands
    2.09
    Bands
    2.08
    Activations Density 0.038%

    No Known Activations