© 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. 25-GEMMASCOPE-RES-16K
    6. 2664
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to troubleshooting and error messages in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.58
     везе
    -0.57
     وتسجيلات
    -0.54
     الدولى
    -0.51
    RenderAtEndOf
    -0.50
    webElementGuid
    -0.50
    帖最后由
    -0.49
    LITERAL
    -0.48
    ERSHIP
    -0.48
    richTextPanel
    -0.47
    POSITIVE LOGITS
     males
    0.70
     graves
    0.63
     problemas
    0.60
     problems
    0.60
     defaultstate
    0.59
    TargetException
    0.59
    argout
    0.58
    PageRoute
    0.57
     difficulties
    0.57
    困难
    0.55
    Activations Density 0.039%

    No Known Activations