© 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. 18-GEMMASCOPE-RES-16K
    11. 8295
    Prev
    Next
    INDEX
    Explanations

    expressions of optimism and hopefulness

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

    Expressing possibility or capability

    np_acts-logits-general · gemini-2.0-flash

    it can be done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.61
     CURIAM
    -0.58
    findpost
    -0.50
    BeginContext
    -0.48
    一方面
    -0.47
    fortawesome
    -0.47
     meanwhile
    -0.46
     måtte
    -0.45
    でしょうね
    -0.44
    ntgen
    -0.44
    POSITIVE LOGITS
     achievable
    1.02
     can
    0.97
     doable
    0.92
     possibility
    0.88
     attainable
    0.86
     possibilities
    0.83
    can
    0.81
    是可以
    0.77
     capable
    0.77
     feasible
    0.76
    Activations Density 0.281%

    No Known Activations