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. 8-GEMMASCOPE-RES-16K
    6. 14934
    Prev
    Next
    INDEX
    Explanations

    references to ownership and the dynamics of power relationships, particularly in the context of slavery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.74
    AutoScaleMode
    -0.71
    AddTagHelper
    -0.71
     doInBackground
    -0.71
    AndEndTag
    -0.70
    
    -0.68
    WaitGroup
    -0.67
     виправивши
    -0.66
    ConstraintMaker
    -0.62
    örté
    -0.57
    POSITIVE LOGITS
    ValueGenerated
    0.54
    uf
    0.49
     satisfait
    0.46
    InjectAttribute
    0.46
     неде
    0.46
    EndProject
    0.44
    :"-"`
    0.42
    收
    0.42
    }{}
    0.42
    遣
    0.42
    Activations Density 0.491%

    No Known Activations