© 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. 15-GEMMASCOPE-RES-16K
    6. 4954
    Prev
    Next
    INDEX
    Explanations

    punctuations and grammatical structures indicating sentence boundaries or pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.87
    parsedMessage
    -0.81
    TargetException
    -0.77
    ()?;
    -0.76
     صوتيه
    -0.75
     Anſ
    -0.74
    ArrowToggle
    -0.74
     purpoſe
    -0.74
     חיצוניים
    -0.72
     Мексичка
    -0.71
    POSITIVE LOGITS
     koska
    0.43
     Dương
    0.41
     אחר
    0.40
    เพราะ
    0.40
     دیده
    0.40
     נגד
    0.40
     deoarece
    0.40
     crescer
    0.40
    coral
    0.39
     desaparecido
    0.39
    Activations Density 0.293%

    No Known Activations