© 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. 2-GEMMASCOPE-RES-16K
    6. 1806
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.28
    ↵↵
    -1.12
    <eos>
    -1.04
    ↵↵↵
    -0.91
    ↵↵↵↵
    -0.81
    ↵↵↵↵↵
    -0.74
    ↵↵↵↵↵↵
    -0.63
    ↵↵↵↵↵↵↵
    -0.61
    ↵↵↵↵↵↵↵↵
    -0.58
    ↵↵↵↵↵↵↵↵↵
    -0.57
    POSITIVE LOGITS
    ^(@)
    0.97
    tvguidetime
    0.90
    LLocation
    0.87
    archiviato
    0.83
    ConstraintMaker
    0.83
    berdayakan
    0.83
    AxisAlignment
    0.82
    EDEFAULT
    0.80
    లాలు
    0.80
     rêves
    0.79
    Activations Density 1.604%

    No Known Activations