Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5353
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and experimental methodology

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

    preceding types of bodily fluids

    np_acts-logits-general · gemini-2.0-flash

    primary, intermediate, complete, natural, extended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.47
     either
    -0.45
     by
    -0.41
    for
    -0.41
     with
    -0.39
    1
    -0.38
    in
    -0.38
     from
    -0.37
    They
    -0.37
    that
    -0.37
    POSITIVE LOGITS
    <unused28>
    1.26
    <unused16>
    1.26
    <unused74>
    1.26
    <unused79>
    1.26
    <unused52>
    1.26
    <unused68>
    1.26
    <unused8>
    1.25
    <unused14>
    1.25
    <unused3>
    1.25
    [@BOS@]
    1.25
    Activations Density 1.735%

    No Known Activations