Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9570
    Prev
    Next
    INDEX
    Explanations

    instances of underscore-prefixed terms, likely representing variables or functions in code or technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewType
    -0.83
    ")));
    
    -0.81
    hips
    -0.77
    StoryboardSegue
    -0.77
    getOutputStream
    -0.77
    )"),
    -0.76
    Портали
    -0.76
    chtenstein
    -0.76
     AssemblyVersion
    -0.75
     itſelf
    -0.73
    POSITIVE LOGITS
    _
    1.43
    \_
    1.21
    &_
    1.13
     _
    1.12
    +"_
    1.06
    '_
    1.06
    ]_
    1.06
     *_
    1.04
    ._
    1.04
     "_
    1.03
    Activations Density 0.529%

    No Known Activations