© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1304
    Prev
    Next
    INDEX
    Explanations

    elements related to medical diagnoses and their implications

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

    ending in "l"

    np_acts-logits-general · gemini-2.0-flash

    l followed by tech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    })`
    -0.34
    $")
    -0.32
    Aholisi
    -0.32
    |')
    -0.32
    %",
    -0.32
    %")
    -0.31
    >')
    -0.30
    ]),
    
    -0.30
    ").
    -0.29
    !",
    -0.29
    POSITIVE LOGITS
     AssemblyCulture
    0.83
    IBOutlet
    0.66
    adaptiveStyles
    0.64
    transQ
    0.63
    MigrationBuilder
    0.63
    PMailer
    0.62
    zzleHttp
    0.61
    
    0.61
    достатки
    0.60
    URLException
    0.60
    Activations Density 0.462%

    No Known Activations