© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7785
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional scenarios and recommendations

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

    the word "a" or articles appearing before nouns in technical and instructional contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.71
     snippetHide
    -0.69
     something
    -0.64
     AssemblyTitle
    -0.61
     المعيارى
    -0.60
     ſoll
    -0.56
     jsPsych
    -0.55
    }}]{
    -0.55
    [@BOS@]
    -0.54
    <unused8>
    -0.54
    POSITIVE LOGITS
     a
    0.90
     A
    0.39
    WriteBarrier
    0.37
    A
    0.35
    uxxxx
    0.33
     administrativos
    0.29
    dafx
    0.29
    SizeMode
    0.29
     创建时间
    0.28
    യും
    0.28
    Activations Density 0.757%

    No Known Activations