© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16128
    Prev
    Next
    INDEX
    Explanations

    technical terms related to printing and material science

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

    after coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Says
    -0.70
    Adds
    -0.60
     sanoo
    -0.59
     Says
    -0.57
    美味しいです
    -0.55
    ține
    -0.55
    ಿದೆ
    -0.53
    と思っています
    -0.52
     می‌گوید
    -0.52
    いますが
    -0.51
    POSITIVE LOGITS
     was
    2.57
     wasn
    2.11
     had
    1.99
    was
    1.96
     were
    1.93
     seemed
    1.88
     weren
    1.80
     didn
    1.79
    wasn
    1.75
     wasnt
    1.72
    Activations Density 2.220%

    No Known Activations