© 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. 20-GEMMASCOPE-RES-16K
    6. 1452
    Prev
    Next
    INDEX
    Explanations

    code structures related to error handling and HTTP request management

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

    error handling and system exit codes in programming scripts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     चीज़ों
    -0.38
     sought
    -0.31
     beef
    -0.30
    AndEndTag
    -0.30
    TemporalType
    -0.30
     Administrativna
    -0.30
     Superan
    -0.30
    extAlignment
    -0.29
     Савезне
    -0.29
     Италијани
    -0.29
    POSITIVE LOGITS
    WebControls
    0.61
     <=",
    0.54
    enderror
    0.54
    <?
    0.51
    eseorang
    0.50
     unsafe
    0.49
    msgTypes
    0.48
     coraggio
    0.47
     insecure
    0.47
    OCCURRED
    0.46
    Activations Density 0.163%

    No Known Activations