© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6945
    Prev
    Next
    INDEX
    Explanations

    numeric values and specific function-related symbols from programming

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

    Followed by colon, then starts with "Q"

    np_acts-logits-general · gemini-2.0-flash

    uv or sec

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.99
    }}$.
    -0.75
    "].
    -0.69
    ".
    -0.68
     }}$.
    -0.68
    ."
    -0.67
    }}.
    -0.64
    ].
    -0.64
    }'.
    -0.61
    '].
    -0.60
    POSITIVE LOGITS
    ConstraintMaker
    0.96
    IntoConstraints
    0.82
     transférez
    0.80
     للاسماء
    0.79
     propOrder
    0.77
    ValueStyle
    0.72
    AddTagHelper
    0.72
     الحره
    0.71
    imageshack
    0.71
    GEBURTSDATUM
    0.67
    Activations Density 0.608%

    No Known Activations