© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 8845
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and formatting related to equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >");
    
    -0.58
    "},
    
    -0.56
    onshire
    -0.56
    ⎠
    -0.54
    }],
    
    -0.54
    }))
    
    -0.54
    "):
    
    -0.53
    '>
    
    -0.52
    )");
    
    -0.52
    '))
    
    -0.51
    POSITIVE LOGITS
    enumi
    0.54
     nakalista
    0.43
    AndEndTag
    0.42
     aparcamiento
    0.41
    MemoryWarning
    0.40
    drawiam
    0.39
     ever
    0.39
     noiva
    0.39
    Garantía
    0.39
     incomplète
    0.38
    Activations Density 0.351%

    No Known Activations