© 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. 3390
    Prev
    Next
    INDEX
    Explanations

    various types of parentheses and brackets in the text

    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
     kasarigan
    -0.76
    ArrowToggle
    -0.69
     ब्रेकडाउन
    -0.65
    Ӕ
    -0.63
    WritableDatabase
    -0.62
    ніципа
    -0.60
     surla
    -0.59
    ngdoc
    -0.59
    TagMode
    -0.59
    رشف
    -0.59
    POSITIVE LOGITS
     weten
    0.43
    InputTagHelper
    0.39
     were
    0.39
     seseorang
    0.35
    händler
    0.34
     means
    0.34
    bebasan
    0.34
     sesuatu
    0.32
     someone
    0.31
    angaben
    0.31
    Activations Density 0.122%

    No Known Activations