© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2945
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to file paths, particularly related to code and databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    codes or paths within a programming context

    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
     lightening
    -0.38
     UST
    -0.37
     genie
    -0.37
    impinan
    -0.35
     HRT
    -0.35
     bailey
    -0.34
     reformat
    -0.34
     IGN
    -0.34
     LNB
    -0.34
     CTS
    -0.34
    POSITIVE LOGITS
     kasarigan
    0.85
    눠
    0.76
    !*\
    0.72
    거나
    0.70
    ThroughAttribute
    0.69
    JspWriter
    0.68
     betweenstory
    0.66
    댔
    0.65
    ніципа
    0.64
    듯
    0.63
    Activations Density 0.025%

    No Known Activations