© 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. 11-GEMMASCOPE-RES-16K
    6. 6615
    Prev
    Next
    INDEX
    Explanations

    units of measurement, particularly related to size and distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ")==
    -0.68
    ”—
    -0.66
    wies
    -0.63
    ]")
    -0.63
    FIF
    -0.62
    ••••
    -0.61
     FIF
    -0.58
    ))-
    -0.57
    ]");
    -0.57
    :");
    -0.57
    POSITIVE LOGITS
     metres
    1.03
     km
    1.01
    km
    0.89
     Meters
    0.87
     MainAxisSize
    0.86
     kilometres
    0.86
     meters
    0.84
     kms
    0.83
    Personendaten
    0.82
    metres
    0.82
    Activations Density 0.288%

    No Known Activations