© 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. 15-GEMMASCOPE-RES-16K
    6. 2947
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and statements involving hypothetical situations

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

    conditional statements and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realizing
    -0.45
     Fichier
    -0.43
    Actually
    -0.43
     Actually
    -0.41
    <bos>
    -0.40
    iją
    -0.39
     actually
    -0.39
    atific
    -0.38
     Independencia
    -0.37
    derive
    -0.37
    POSITIVE LOGITS
    StoryboardSegue
    0.90
    :✨
    0.84
    Personensuche
    0.77
    SharedCtor
    0.74
     ProtoMessage
    0.72
    Демографія
    0.71
    anything
    0.70
    MigrationBuilder
    0.69
    bootstrapcdn
    0.67
    windowFixed
    0.67
    Activations Density 0.198%

    No Known Activations