© 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. 24-GEMMASCOPE-RES-16K
    11. 4628
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure in programming

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

    Protocol buffer data types

    np_acts-logits-general · gemini-2.0-flash

    packed, optional, singular, repeated fields

    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
    TestingModule
    -0.60
    migrationBuilder
    -0.58
     ***!
    -0.52
     ligiloj
    -0.44
    DebuggerNonUser
    -0.43
     TestBed
    -0.42
    Tikang
    -0.42
     Réponses
    -0.41
     הה
    -0.41
    зяй
    -0.40
    POSITIVE LOGITS
     boolean
    1.11
    boolean
    1.06
     bool
    1.05
     Bool
    1.05
    bool
    1.02
    Bool
    1.00
     integer
    1.00
     float
    0.98
     int
    0.98
     string
    0.97
    Activations Density 0.959%

    No Known Activations