© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5606
    Prev
    Next
    INDEX
    Explanations

    terms related to addiction treatment and medication interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artificiales
    -0.52
    Попис
    -0.52
     Amad
    -0.52
     lightsaber
    -0.51
    期刊论文
    -0.50
    }}}{\
    -0.50
     slaughtered
    -0.49
    norr
    -0.49
     Balth
    -0.49
     whistled
    -0.49
    POSITIVE LOGITS
     addiction
    1.21
     sobriety
    1.17
     recovery
    1.16
    Addiction
    1.09
     Alcoholic
    1.07
     rehab
    1.03
     addict
    1.02
     addicts
    1.01
     Addiction
    1.01
     alcoholic
    0.99
    Activations Density 0.255%

    No Known Activations