© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13134
    Prev
    Next
    INDEX
    Explanations

    chemical compound names or characteristics related to solid-state substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.49
    vature
    -0.49
    ljen
    -0.49
    gnac
    -0.48
    atyw
    -0.45
     live
    -0.44
    ReusableCell
    -0.44
    TargetException
    -0.43
    grà
    -0.43
    龄
    -0.43
    POSITIVE LOGITS
     crystallized
    0.77
     purity
    0.74
     crystals
    0.69
     crystalline
    0.68
     crystal
    0.68
     recrystal
    0.66
     purify
    0.62
     Purity
    0.62
     purification
    0.62
     melting
    0.61
    Activations Density 0.990%

    No Known Activations