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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7820
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "self" in coding contexts, particularly in programming functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /$',
    -0.34
     мәкалә
    -0.31
     والك
    -0.31
    ']));
    -0.28
    cemic
    -0.27
     rico
    -0.26
     điệu
    -0.26
    ResumeLayout
    -0.26
     f
    -0.26
    进制
    -0.25
    POSITIVE LOGITS
    MigrationBuilder
    0.69
    parsedMessage
    0.68
     ExecuteAsync
    0.65
    WriteTagHelper
    0.65
    PreInfinity
    0.63
    SourceChecksum
    0.63
    UserScript
    0.63
     MonoBehaviour
    0.61
     ControllerBase
    0.59
    CloseOperation
    0.59
    Activations Density 0.235%

    No Known Activations