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. 9-GEMMASCOPE-RES-16K
    6. 15531
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those related to code structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Past
    -0.50
     pop
    -0.50
     지
    -0.46
    rettes
    -0.44
     past
    -0.44
     Barb
    -0.44
     popup
    -0.43
     http
    -0.43
     Web
    -0.42
     fa
    -0.41
    POSITIVE LOGITS
    mybatisplus
    0.83
    Datuak
    0.82
     createSlice
    0.82
    الدراسه
    0.81
    WriteAttribute
    0.79
    ChildScrollView
    0.74
     StatelessWidget
    0.74
     useStyles
    0.70
     NSCoder
    0.70
     المعيارى
    0.70
    Activations Density 0.732%

    No Known Activations