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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6086
    Prev
    Next
    INDEX
    Explanations

    related structures and syntax within programming code

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

    Code-related texts and syntax

    np_acts-logits-general · gemini-2.0-flash

    `ListenableFuture`, `APIRequest`, `executeAsync`

    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
     surla
    -0.71
     <=",
    -0.65
    +:+
    -0.60
    脚注の使い方
    -0.59
    SBATCH
    -0.59
     Infórmanos
    -0.58
    ----</
    -0.58
    LookAnd
    -0.57
     متعلقه
    -0.57
    TargetException
    -0.57
    POSITIVE LOGITS
     amarillas
    0.36
    ?
    0.35
    Following
    0.34
     demografica
    0.34
     because
    0.34
    Because
    0.33
    because
    0.32
    fully
    0.32
     Following
    0.31
     føl
    0.31
    Activations Density 0.058%

    No Known Activations