© 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-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15475
    Prev
    Next
    INDEX
    Explanations

    reported speech and quotations from speakers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     traditionnels
    -0.56
     dasarnya
    -0.55
    
    -0.54
     poffible
    -0.53
     vostri
    -0.53
     zijne
    -0.52
    troppo
    -0.52
     nikdy
    -0.52
     '\\;'
    -0.51
     stessi
    -0.50
    POSITIVE LOGITS
    ]=>
    0.48
     coach
    0.43
     fellow
    0.40
     former
    0.37
    __);
    0.37
     senior
    0.36
     a
    0.36
     the
    0.36
    enumii
    0.35
     said
    0.34
    Activations Density 0.070%

    No Known Activations