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. 7-GEMMASCOPE-RES-16K
    6. 8875
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those involving initialization, assignments, and expressions in code

    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
     جغرافيا
    -0.64
    Datuak
    -0.59
     חיצוניים
    -0.54
     везе
    -0.54
     وتسجيلات
    -0.54
    JAKARTA
    -0.52
     AspNetCore
    -0.51
     ✭✭
    -0.50
    hdys
    -0.49
     lenker
    -0.49
    POSITIVE LOGITS
    ]")]
    0.69
    ReusableCell
    0.68
    InitVars
    0.65
    awakeFromNib
    0.62
    WriteBarrier
    0.60
    initializeApp
    0.57
    typeorm
    0.56
     createSlice
    0.56
    iprot
    0.54
    '">
    0.54
    Activations Density 0.736%

    No Known Activations