© 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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1475
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly in languages like JavaScript and C-like languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Creator
    -0.41
     belast
    -0.39
     initial
    -0.35
    motor
    -0.35
     Creative
    -0.35
     cataly
    -0.34
    GEBURTS
    -0.34
     Motor
    -0.33
    انه
    -0.33
    llar
    -0.33
    POSITIVE LOGITS
    GOTREF
    0.68
    EndContext
    0.64
     endwhile
    0.63
    BagLayout
    0.62
    endforeach
    0.62
     betweenstory
    0.60
     iprot
    0.58
     AssemblyCulture
    0.58
     endforeach
    0.58
     noDo
    0.57
    Activations Density 0.095%

    No Known Activations