© 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. 23-GEMMASCOPE-RES-16K
    6. 9359
    Prev
    Next
    INDEX
    Explanations

    references to porous materials or related terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    value
    -0.54
    Value
    -0.54
     value
    -0.53
    ForValue
    -0.52
    criminator
    -0.48
     Value
    -0.47
    #
    -0.46
    makeText
    -0.46
    ValueOf
    -0.44
     policy
    -0.44
    POSITIVE LOGITS
    RegressionTest
    0.66
    yntaxException
    0.63
    afficheront
    0.61
    脚注の使い方
    0.60
    Hentet
    0.58
    Portale
    0.58
    CodedInputStream
    0.55
    apnews
    0.55
    pédie
    0.54
    enderror
    0.54
    Activations Density 0.347%

    No Known Activations