© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    references to underlying systems of authority and control in society

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

    Figures of speech and idioms

    np_acts-logits-general · gemini-2.0-flash

    metaphorical expressions and analogies

    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
     associés
    -0.49
    ########.
    -0.45
     associées
    -0.44
     achten
    -0.42
     renon
    -0.42
    plus
    -0.41
     OnDestroy
    -0.41
    anut
    -0.41
     ferons
    -0.40
    Джерела
    -0.40
    POSITIVE LOGITS
     metaphor
    0.97
     metaphorical
    0.90
     analogy
    0.83
    LookAnd
    0.77
    Diweddarwch
    0.73
     metaphors
    0.71
     صوتيه
    0.71
    InvalidProtocol
    0.71
    writeField
    0.70
    dafx
    0.69
    Activations Density 0.349%

    No Known Activations