© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6677
    Prev
    Next
    INDEX
    Explanations

    code-related terms and class definitions

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

    Code, internal elements and exceptions

    np_acts-logits-general · gemini-2.0-flash

    arturbosch.detekt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     (
    -0.42
    новништво
    -0.36
     justement
    -0.35
     very
    -0.34
    wußt
    -0.34
     โ
    -0.33
     ('
    -0.33
     talaga
    -0.33
     strangely
    -0.32
    hopefully
    -0.32
    POSITIVE LOGITS
     فريبيس
    0.64
    afficheront
    0.60
     MediatR
    0.57
    xnn
    0.56
     HasFactory
    0.56
     ErrInvalid
    0.56
    WebElementEntity
    0.56
     JpaRepository
    0.56
     CommonModule
    0.55
     defStyleAttr
    0.54
    Activations Density 0.259%

    No Known Activations