© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6752
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their manipulation in programming

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

    Code snippets or code-related text

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đối
    -0.36
     night
    -0.35
     sm
    -0.35
    Bonsoir
    -0.35
     partecipazione
    -0.34
     notte
    -0.34
     stră
    -0.33
     ferons
    -0.33
    kijken
    -0.33
    attered
    -0.33
    POSITIVE LOGITS
    ThroughAttribute
    0.84
     surla
    0.65
     pulumi
    0.63
     gynhyrchwyd
    0.60
    bootstrapcdn
    0.59
     GenerationType
    0.58
    verwijspagina
    0.58
     iprot
    0.58
    Portály
    0.58
    WebpackPlugin
    0.57
    Activations Density 0.219%

    No Known Activations