© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2933
    Prev
    Next
    INDEX
    Explanations

    patterns of data organized in a structure resembling programming code or function definitions

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

    different types of delimiters and formatting in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edelman
    -0.49
    nex
    -0.49
    ilan
    -0.49
    Parameterized
    -0.47
    atom
    -0.47
     teratur
    -0.46
    ()]
    
    -0.46
    itsi
    -0.46
     campagna
    -0.45
    ishna
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    1.03
    ConstraintMaker
    1.02
    extAlignment
    0.94
     وتسجيلات
    0.92
     للمعارف
    0.91
    +#+
    0.90
    存于互联网档案馆
    0.89
    Tembelea
    0.89
    verwijspagina
    0.88
     resourceCulture
    0.88
    Activations Density 0.649%

    No Known Activations