© 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. 13706
    Prev
    Next
    INDEX
    Explanations

    mentions of items and experiences related to gifts and celebrations

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

    a change of subject

    np_acts-logits-general · gemini-2.0-flash

    contrast or concession

    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
    Autoritní
    -0.74
     كومونز
    -0.74
    balleur
    -0.60
    がありますが
    -0.57
    Geografía
    -0.57
    ammans
    -0.55
    новништво
    -0.55
     Roskov
    -0.54
    ⤹
    -0.54
    internalType
    -0.51
    POSITIVE LOGITS
     anyway
    4.02
     anyways
    3.29
    anyway
    3.21
     anyhow
    2.81
     Anyway
    2.81
    Anyway
    2.73
     nonetheless
    2.35
     Anyways
    2.20
     nevertheless
    2.17
    Anyways
    2.05
    Activations Density 0.331%

    No Known Activations