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. 14-GEMMASCOPE-RES-16K
    6. 10627
    Prev
    Next
    INDEX
    Explanations

    phrases indicating decision-making or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.58
     Clap
    -0.56
    Nazionale
    -0.56
     jLabel
    -0.56
     Rutland
    -0.55
    >",
    -0.55
    )});
    -0.55
    lotto
    -0.54
     Ause
    -0.54
     ABCD
    -0.53
    POSITIVE LOGITS
    حياتها
    0.74
     decided
    0.72
    GenerationType
    0.67
    
    0.61
    uesia
    0.61
     use
    0.61
     rather
    0.60
     forego
    0.60
     instead
    0.60
    AsStream
    0.60
    Activations Density 0.210%

    No Known Activations