© 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. 17-GEMMASCOPE-RES-16K
    6. 4961
    Prev
    Next
    INDEX
    Explanations

    variables and identifiers related to data structures and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.56
    ;
    -0.56
    ;
    -0.55
    __':
    -0.53
    igens
    -0.51
    EndGlobalSection
    -0.51
     übrigens
    -0.49
    ].(
    -0.49
    othelioma
    -0.49
     sẻ
    -0.48
    POSITIVE LOGITS
     !=
    0.80
    리가
    0.79
    TestingModule
    0.78
     !==
    0.74
     wasn
    0.68
    hasOwnProperty
    0.68
    ftagPool
    0.66
     ==
    0.66
     exists
    0.65
     <=
    0.65
    Activations Density 0.218%

    No Known Activations