© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7839
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.84
     Wiktionnaire
    -0.82
    LookAnd
    -0.80
    <unused52>
    -0.77
    <unused68>
    -0.77
     surla
    -0.77
    <unused14>
    -0.77
    <unused8>
    -0.77
    [@BOS@]
    -0.76
    <unused16>
    -0.76
    POSITIVE LOGITS
     pri
    0.34
     perek
    0.31
    lindungi
    0.31
     v
    0.30
     vuestros
    0.28
     otra
    0.28
     professora
    0.27
     övers
    0.27
    ͡
    0.27
     semej
    0.26
    Activations Density 0.199%

    No Known Activations