© 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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4632
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to loading and manipulating data

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

    Reads code elements

    np_acts-logits-general · gemini-2.0-flash

    reading or decoding data structures

    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
     myſelf
    -0.90
    ValueStyle
    -0.76
    tagHelperRunner
    -0.73
     kasarigan
    -0.73
     ainfi
    -0.71
    berdayakan
    -0.70
     houſe
    -0.66
    AddTagHelper
    -0.66
    ſelves
    -0.65
    脚注の使い方
    -0.65
    POSITIVE LOGITS
    lah
    0.39
     next
    0.35
    rd
    0.33
    do
    0.32
    rs
    0.32
    ടു
    0.31
    rb
    0.31
    fscanf
    0.31
     until
    0.31
    read
    0.31
    Activations Density 0.251%

    No Known Activations