© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6008
    Prev
    Next
    INDEX
    Explanations

    instances of collaborative or collective actions and expressions related to personal requests or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conjunctions followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    actions and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.73
    }")]
    -0.70
    }))
    
    -0.67
    '])->
    -0.64
    }),
    
    -0.63
    }));
    
    -0.63
     insuffisamment
    -0.62
    "]));
    -0.62
    ')))
    -0.61
    ']?>
    -0.59
    POSITIVE LOGITS
     build
    0.61
     be
    0.58
     climb
    0.56
     sell
    0.54
     weld
    0.54
     kill
    0.54
     unload
    0.54
     move
    0.53
     grow
    0.52
    spend
    0.52
    Activations Density 0.366%

    No Known Activations