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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5808
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or conditions

    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
     réalis
    -0.66
     Monfieur
    -0.65
     supérieurs
    -0.65
     enfans
    -0.64
     giallo
    -0.62
     ſeveral
    -0.61
     énergé
    -0.61
     quelcon
    -0.61
    charging
    -0.60
     automatiques
    -0.60
    POSITIVE LOGITS
     successfully
    0.72
     finally
    0.72
    Datuak
    0.69
     actually
    0.66
     Respectfully
    0.65
     held
    0.64
    Respectfully
    0.64
     quickly
    0.64
     gradually
    0.63
    woordig
    0.63
    Activations Density 0.927%

    No Known Activations