© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13830
    Prev
    Next
    INDEX
    Explanations

    terms relating to genetic mutations and their detection

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

    Genetic mutations

    np_acts-logits-general · gemini-2.0-flash

    genetic mutations detected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     referenties
    -0.53
    енча
    -0.53
     חיצוניים
    -0.53
    shadowOffset
    -0.52
    Réalisation
    -0.52
     poveznice
    -0.49
     interconnection
    -0.48
     Hatch
    -0.48
    ತ್
    -0.47
    が終わ
    -0.47
    POSITIVE LOGITS
     mutations
    1.20
     mutation
    1.18
     Mutation
    0.97
     mutant
    0.95
     Mutations
    0.92
     miss
    0.90
     mutated
    0.90
    mutations
    0.88
     mut
    0.86
    mutation
    0.84
    Activations Density 2.138%

    No Known Activations