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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5778
    Prev
    Next
    INDEX
    Explanations

    expressions related to career progression and personal achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     således
    -0.71
     BTW
    -0.57
     '..
    -0.55
     nemlig
    -0.55
     ~$
    -0.54
     ALSO
    -0.53
    https
    -0.52
     siis
    -0.52
     voici
    -0.52
    ..)
    -0.52
    POSITIVE LOGITS
     lads
    0.70
    SBATCH
    0.68
     Vordergrund
    0.63
     bits
    0.61
     كومونز
    0.59
     оригіналу
    0.59
    proper
    0.58
     [
    0.58
    massive
    0.57
    getMenuInflater
    0.57
    Activations Density 0.096%

    No Known Activations