© 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. 15-GEMMASCOPE-RES-16K
    11. 1941
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers related to scientific concepts, entities, or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".
    -0.69
    .");
    -0.69
    ].
    -0.68
    ®.
    -0.68
    ”.
    -0.68
    **.
    -0.66
    ).
    -0.66
    .
    -0.66
    %.
    -0.65
    ）.
    -0.65
    POSITIVE LOGITS
     will
    0.96
     would
    0.95
     was
    0.90
     could
    0.89
     is
    0.86
     shall
    0.84
     adalah
    0.84
    지는
    0.84
    리는
    0.82
    들은
    0.81
    Activations Density 2.146%

    No Known Activations