© 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. 16-GEMMASCOPE-RES-16K
    11. 1249
    Prev
    Next
    INDEX
    Explanations

    concepts related to interconnected systems and structures

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

    Figurative language and metaphors

    np_acts-logits-general · gemini-2.0-flash

    metaphorical uses of common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.48
    logii
    -0.46
     OnDestroy
    -0.46
    Dado
    -0.44
    готовка
    -0.43
    GraphicsUnit
    -0.43
    zulegen
    -0.41
     Fre
    -0.41
    률
    -0.40
    ┗
    -0.40
    POSITIVE LOGITS
     metaphor
    0.87
     defaultstate
    0.79
    Portail
    0.77
     analogy
    0.76
     betweenstory
    0.74
     metaphorical
    0.74
     متعلقه
    0.73
    dafx
    0.71
    ConstraintMaker
    0.71
     الحره
    0.70
    Activations Density 0.331%

    No Known Activations