© 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. 4-GEMMASCOPE-RES-16K
    6. 918
    Prev
    Next
    INDEX
    Explanations

    data structure types and their implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.49
    ,
    -0.49
     plus
    -0.47
    hem
    -0.44
    asion
    -0.43
    enderror
    -0.42
     #
    -0.42
    chtenstein
    -0.42
    लाइन
    -0.42
    让她
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.92
     FetchType
    0.89
    emptyList
    0.88
     snippetHide
    0.86
     IList
    0.84
     LinkedHashMap
    0.83
    toList
    0.83
     listOf
    0.82
     List
    0.82
    IList
    0.80
    Activations Density 0.170%

    No Known Activations