© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4834
    Prev
    Next
    INDEX
    Explanations

    expressions of honor and recognition for individuals, particularly in military or service contexts

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

    Text inside quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quotations and speech attributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /');
    -0.57
    /
    -0.56
    näm
    -0.53
     disgruntled
    -0.53
     unknowingly
    -0.51
     detrimental
    -0.51
     detriment
    -0.50
    Actualmente
    -0.50
    /';
    -0.50
     supuestamente
    -0.50
    POSITIVE LOGITS
     Majefty
    0.74
    XmlAccessType
    0.73
    IVEREF
    0.73
     AssemblyCulture
    0.70
     ―――――
    0.69
     purpoſe
    0.68
    HasForeignKey
    0.67
    PreExecute
    0.67
     كومونز
    0.66
     estekak
    0.65
    Activations Density 0.221%

    No Known Activations