Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15765
    Prev
    Next
    INDEX
    Explanations

    statements about societal conditions and personal choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    +#+#
    -0.77
    OGND
    -0.76
    parsedMessage
    -0.75
     surla
    -0.70
     Signalez
    -0.69
    WithIOException
    -0.66
    Cyfarwyddwr
    -0.65
     Biôgrafia
    -0.64
    SBATCH
    -0.62
    MessageState
    -0.60
    POSITIVE LOGITS
    MathML
    0.34
    Construct
    0.31
    Lifecycle
    0.31
    construct
    0.30
     zob
    0.29
    edit
    0.28
    构造
    0.27
    Instance
    0.27
    an
    0.27
    constru
    0.27
    Activations Density 0.450%

    No Known Activations