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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 12106
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to data transmission and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.06
    ってみて
    -0.68
     Roskov
    -0.63
    ってみました
    -0.60
    }],
    
    -0.59
    ってみる
    -0.59
     ")");
    -0.59
    '])->
    -0.59
    }),
    
    -0.57
     kaarangay
    -0.56
    POSITIVE LOGITS
    bootstrapcdn
    1.24
    InputBorder
    1.08
     BoxDecoration
    1.02
    WebVitals
    0.95
    ConstraintMaker
    0.90
    GraphicsUnit
    0.81
     BoxFit
    0.80
    LLocation
    0.80
     InputDecoration
    0.78
    ImageContext
    0.78
    Activations Density 13.463%

    No Known Activations