© 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. 25-GEMMASCOPE-RES-16K
    11. 1118
    Prev
    Next
    INDEX
    Explanations

    references to magical or enhanced weaponry and combat abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.64
     CWE
    -0.63
    ⓧ
    -0.60
     المعيارى
    -0.60
    jooq
    -0.59
    __((
    -0.56
    LEEP
    -0.54
     ivelany
    -0.53
    lüğ
    -0.51
    DIPSETTING
    -0.50
    POSITIVE LOGITS
     charged
    0.63
     unleash
    0.63
     charging
    0.63
     lung
    0.63
     brand
    0.61
     launch
    0.60
     launched
    0.59
     launching
    0.59
     trasform
    0.59
     Charge
    0.59
    Activations Density 0.395%

    No Known Activations