© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1101
    Prev
    Next
    INDEX
    Explanations

    phrases and words indicating the act of reaching or access

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

    verbs or phrases related to spreading, reaching, or accessing something.

    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
     endblock
    -0.49
     plantation
    -0.44
    enumi
    -0.44
     software
    -0.42
     /*#__
    -0.41
     vendors
    -0.40
    blum
    -0.39
    الدراسه
    -0.38
    <bos>
    -0.38
     wigs
    -0.38
    POSITIVE LOGITS
    reach
    1.24
     reach
    1.23
     Reach
    1.19
     REACH
    1.17
    Reach
    1.16
     reached
    1.13
     reaches
    1.12
    reached
    1.12
    REACH
    1.05
    Reaching
    1.05
    Activations Density 0.050%

    No Known Activations