© 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. 0-GEMMASCOPE-RES-16K
    6. 2988
    Prev
    Next
    INDEX
    Explanations

    references to a central location or focal point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.47
     صوتيه
    -0.46
     saites
    -0.45
     Charg
    -0.44
    quelize
    -0.41
     IBOutlet
    -0.40
     Altern
    -0.40
    Chall
    -0.39
    }],
    
    -0.39
     ArrayAdapter
    -0.38
    POSITIVE LOGITS
     center
    0.98
     centre
    0.97
    centre
    0.78
     centers
    0.73
     centres
    0.68
     CENTRE
    0.61
    Centre
    0.59
    center
    0.57
     centro
    0.56
     Centre
    0.56
    Activations Density 0.346%

    No Known Activations