© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 15203
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remove" and its variations, indicating a focus on deletion or extraction

    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
     bArr
    -0.78
    AsUp
    -0.75
    Portale
    -0.72
     Stuart
    -0.71
     Schuster
    -0.70
    pity
    -0.69
    };*/
    -0.66
     fact
    -0.65
    ?}",
    -0.63
    
    -0.63
    POSITIVE LOGITS
     Removal
    1.61
     REMOVE
    1.60
     Remove
    1.60
     removal
    1.59
    Remove
    1.54
     removals
    1.53
     REMOV
    1.53
     remove
    1.49
     removed
    1.47
     Removes
    1.47
    Activations Density 0.079%

    No Known Activations