© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10514
    Prev
    Next
    INDEX
    Explanations

    opening and closing brackets and braces in LaTeX code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX or math symbols

    np_acts-logits-general · gemini-2.0-flash

    LaTeX commands and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    jgl
    -0.45
    <?
    -0.43
    __":
    -0.42
    uxxxx
    -0.42
    bibfield
    -0.42
     <<<<<<<<<<<<<<
    -0.42
    內容簡介
    -0.41
    __":
    -0.41
    queryInterface
    -0.40
    ンダント
    -0.40
    POSITIVE LOGITS
     MainAxisSize
    0.52
    [
    0.46
     tolerances
    0.43
    ATTN
    0.40
    elif
    0.40
     Armed
    0.38
    lavia
    0.38
    DockStyle
    0.38
    jupiter
    0.36
    Armed
    0.36
    Activations Density 0.073%

    No Known Activations