© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8522
    Prev
    Next
    INDEX
    Explanations

    terms related to advice or guidelines, particularly in a specific context

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

    Japanese words or phrases

    np_acts-logits-general · gemini-2.0-flash

    Japanese grammatical constructions

    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
    @[+][
    -0.62
     škoda
    -0.60
    MergeFrom
    -0.59
    Rujukan
    -0.55
    ítja
    -0.54
     كومونز
    -0.53
    sphase
    -0.52
    verständlich
    -0.51
    siapkan
    -0.50
    antaranya
    -0.50
    POSITIVE LOGITS
     Starship
    0.57
    UserScript
    0.56
    []
    
    0.52
     actrice
    0.52
    strophy
    0.50
    gameserver
    0.50
    covers
    0.50
     boî
    0.50
    }}_{\
    0.50
     Rebellion
    0.49
    Activations Density 0.079%

    No Known Activations