© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3118
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and method calls in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
     ainfi
    -0.68
    存于互联网档案馆
    -0.63
     Perſ
    -0.60
     Houſe
    -0.58
     houſe
    -0.57
    iffance
    -0.55
    iſh
    -0.54
     contextLoads
    -0.53
     للمعارف
    -0.52
     pleaſure
    -0.50
    POSITIVE LOGITS
    openqa
    0.43
     getchar
    0.40
    randint
    0.40
    MoveNext
    0.40
     pollin
    0.39
     read
    0.37
    ReadByte
    0.37
    NOPQRST
    0.37
    getline
    0.37
     unknownFields
    0.36
    Activations Density 0.393%

    No Known Activations