© 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. 23-GEMMASCOPE-RES-16K
    11. 12676
    Prev
    Next
    INDEX
    Explanations

    references to the term "human" and related human concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    ArgsConstructor
    -0.78
    ="@+
    -0.71
    oporosis
    -0.67
    NOPQRST
    -0.63
     arşivlendi
    -0.60
     onCreateView
    -0.59
    ANTLR
    -0.59
     فريبيس
    -0.59
    alamualaikum
    -0.57
    Erreferentziak
    -0.57
    POSITIVE LOGITS
     beings
    1.19
    ely
    0.73
    being
    0.68
    oids
    0.66
     being
    0.65
     rights
    0.62
    lijke
    0.62
    ly
    0.61
     race
    0.60
    ized
    0.60
    Activations Density 0.098%

    No Known Activations