Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 62216
    Prev
    Next
    INDEX
    Explanations

    references to legal and administrative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.36
    '],$
    -0.34
     isolato
    -0.33
    Jeografia
    -0.33
     stof
    -0.30
    tingu
    -0.30
    })`
    -0.30
    })
    
    -0.30
    opsida
    -0.30
    riften
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.80
    windowFixed
    0.59
    UseVisualStyle
    0.50
    Configurer
    0.50
    enderror
    0.49
    scenario
    0.47
    ervlak
    0.47
    BufferException
    0.47
    RRect
    0.46
    anor
    0.46
    Activations Density 0.879%

    No Known Activations