© 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. 16212
    Prev
    Next
    INDEX
    Explanations

    topics related to actions and consequences

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

    Japanese words followed by verb endings

    np_acts-logits-general · gemini-2.0-flash

    lie or arrive

    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
     EconPapers
    -0.74
    WebControls
    -0.58
    aarrggbb
    -0.57
    rohr
    -0.57
    URIComponent
    -0.55
     calendriers
    -0.52
     LIRE
    -0.52
    onActivityResult
    -0.51
     Ceiling
    -0.49
    ViewFeatures
    -0.48
    POSITIVE LOGITS
    WireFormatLite
    0.49
    ContextHolder
    0.47
    +:+
    0.47
    ваний
    0.46
    KY
    0.45
    ftagPool
    0.45
    zing
    0.45
     portero
    0.44
    丧
    0.43
     Tash
    0.43
    Activations Density 0.061%

    No Known Activations