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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 300
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and concepts related to biological and medical contexts

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

    Followed by "except" or exclusion

    np_acts-logits-general · gemini-2.0-flash

    all but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APOLIS
    -0.72
     quelquefois
    -0.70
     Normdatei
    -0.70
    })`
    -0.67
     صوتيه
    -0.66
     tantôt
    -0.65
    ']))
    
    -0.64
     fometimes
    -0.62
    )‏
    -0.62
    ArgsConstructor
    -0.62
    POSITIVE LOGITS
     except
    1.54
    except
    1.40
     excepto
    1.29
     including
    1.26
    Except
    1.26
     Except
    1.26
     kecuali
    1.22
     EXCEPT
    1.18
     sauf
    1.16
    including
    1.15
    Activations Density 0.534%

    No Known Activations