© 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. 20-GEMMASCOPE-RES-16K
    6. 2444
    Prev
    Next
    INDEX
    Explanations

    terms related to systematic approaches and operational definitions in a procedural context

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

    programming or technical terminology related to software development and code.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     t
    -0.31
    1
    -0.28
     "
    -0.26
     \
    -0.26
     and
    -0.25
    ↵↵
    -0.25
     m
    -0.24
    8
    -0.24
     $
    -0.24
     bl
    -0.24
    POSITIVE LOGITS
    RenderAtEndOf
    1.16
    ſelben
    0.92
    ſammen
    0.91
     للاسماء
    0.91
    httphttps
    0.88
     ProtoMessage
    0.88
    parsedMessage
    0.84
    KommentareTeilen
    0.84
     queſto
    0.82
    Datuak
    0.82
    Activations Density 1.621%

    No Known Activations