© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13871
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

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

    Profanity and swear words

    np_acts-logits-general · gemini-2.0-flash

    strong negative emotion

    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
    ]]
    -0.73
     niedersachsen
    -0.71
     umgekehrt
    -0.69
    intenant
    -0.67
     Wikiseite
    -0.67
     étoient
    -0.67
     }],
    -0.66
    seguida
    -0.65
     vieles
    -0.64
     giebt
    -0.63
    POSITIVE LOGITS
     fucking
    0.85
     FUCKING
    0.81
    fucking
    0.80
     goddamn
    0.78
    でございます
    0.78
    fuck
    0.77
     fuck
    0.76
    ಠ
    0.74
     fuckin
    0.73
     doth
    0.72
    Activations Density 0.749%

    No Known Activations