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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7899
    Prev
    Next
    INDEX
    Explanations

    coding-related constructs and elements, particularly focusing on control structures, player interactions, skills, and conditional statements

    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
     poffible
    -0.74
     tartalomajánló
    -0.74
     reaſon
    -0.73
     purpoſe
    -0.68
     pleaſure
    -0.68
     مشين
    -0.68
    rrggbb
    -0.66
    AutoScaleMode
    -0.66
     bezeichneter
    -0.65
     fhort
    -0.65
    POSITIVE LOGITS
    elemField
    0.61
    glBindBuffer
    0.53
    awaiter
    0.52
    ftagPool
    0.51
    ActivityCompat
    0.48
     set
    0.48
    CppCodeGen
    0.48
    WebElementEntity
    0.47
    Parameteri
    0.46
    TypedDataSet
    0.46
    Activations Density 0.891%

    No Known Activations