© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 539
    Prev
    Next
    INDEX
    Explanations

    specific syntax patterns or formatting associated with programming or coding elements

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

    specific error messages and confirmation codes related to email and account verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.67
    protoimpl
    -0.55
     initComponents
    -0.54
    libft
    -0.53
    Память
    -0.53
    gatsby
    -0.53
     likes
    -0.52
    GenerationType
    -0.52
    ambut
    -0.52
     للاسماء
    -0.49
    POSITIVE LOGITS
    __":
    
    0.56
    '}),
    0.54
    }}">
    0.54
    '}>
    0.52
    istert
    0.52
    ]<<"
    0.51
    jsonwebtoken
    0.51
    MigrationBuilder
    0.50
    '''
    
    0.50
    opsida
    0.48
    Activations Density 0.015%

    No Known Activations