© 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. 24-GEMMASCOPE-RES-16K
    11. 14441
    Prev
    Next
    INDEX
    Explanations

    instances of proper names and related descriptors

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

    Appositives, especially titles and relationships

    np_acts-logits-general · gemini-2.0-flash

    roles and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.58
    ;";
    -0.57
    .")
    -0.56
    下载附件
    -0.55
    ...")
    -0.53
     Audiodateien
    -0.52
    umbres
    -0.52
    íble
    -0.52
    :")
    -0.51
    tably
    -0.50
    POSITIVE LOGITS
     formerly
    1.09
     aka
    1.04
     owner
    0.99
    formerly
    0.93
     founder
    0.93
     son
    0.92
     better
    0.92
    better
    0.91
     Jr
    0.88
     alias
    0.88
    Activations Density 0.361%

    No Known Activations