© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10935
    Prev
    Next
    INDEX
    Explanations

    specific amino acid substitutions or mutations in protein sequences

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

    Amino acid mutations

    np_acts-logits-general · gemini-2.0-flash

    amino acid mutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.45
    #+#
    -0.41
     Anſ
    -0.40
     ſy
    -0.39
    ſelf
    -0.38
     Reſ
    -0.38
     faſt
    -0.37
     Chriftian
    -0.36
     itſelf
    -0.35
    Inflater
    -0.35
    POSITIVE LOGITS
     mutation
    0.57
     mutations
    0.57
    TargetException
    0.53
    mutation
    0.52
    mutations
    0.52
     mutated
    0.52
    reonine
    0.51
     Mutation
    0.50
     Mutations
    0.50
    mutant
    0.50
    Activations Density 1.250%

    No Known Activations