© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5806
    Prev
    Next
    INDEX
    Explanations

    Java import statements and class definitions

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

    Code-related terms or file paths

    np_acts-logits-general · gemini-2.0-flash

    code snippets and technical terms

    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
    ConstraintMaker
    -0.78
    MessageOf
    -0.65
    ⟬
    -0.63
    enterOuterAlt
    -0.63
    providedIn
    -0.62
     betweenstory
    -0.60
     tričko
    -0.56
    tvguidetime
    -0.56
    AddTagHelper
    -0.53
     étoient
    -0.53
    POSITIVE LOGITS
    layoutControl
    0.38
    wit
    0.33
    ar
    0.32
    通
    0.32
    ULT
    0.32
     بی
    0.32
    vk
    0.32
     خل
    0.32
    Explicación
    0.32
     المص
    0.31
    Activations Density 0.036%

    No Known Activations