© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14059
    Prev
    Next
    INDEX
    Explanations

    elements related to structures or protocols, particularly in programming or coding contexts

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

    Followed by "facility" or "value"

    np_acts-logits-general · gemini-2.0-flash

    code structures with values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    literals
    -0.49
    localVar
    -0.45
     الب
    -0.35
    icking
    -0.35
    干
    -0.35
    stino
    -0.34
    互
    -0.34
     gy
    -0.33
    eddable
    -0.33
    aed
    -0.32
    POSITIVE LOGITS
    UnusedPrivate
    1.00
     propOrder
    0.87
    TargetException
    0.87
     iconTwitter
    0.81
     AssemblyCulture
    0.80
     HasFactory
    0.78
    DebuggerStep
    0.75
    ReferenceEquals
    0.74
    +#+#
    0.73
    NTIS
    0.73
    Activations Density 1.379%

    No Known Activations