© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8054
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and computer science

    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
    ืม
    -0.47
    Grüße
    -0.46
     {:.
    -0.45
    zonder
    -0.44
    zeptember
    -0.43
     Abp
    -0.43
     trần
    -0.43
    VolleyError
    -0.40
     Depends
    -0.40
     Audiodateien
    -0.39
    POSITIVE LOGITS
    ScopeManager
    0.90
    PrototypeOf
    0.68
    XmlAccessType
    0.68
    VersionUID
    0.66
     @"/
    0.61
    getRuntime
    0.60
     صوتيه
    0.59
    enterOuterAlt
    0.59
    StoryboardSegue
    0.59
    tagext
    0.59
    Activations Density 0.619%

    No Known Activations