© 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. 18-GEMMASCOPE-RES-16K
    6. 8842
    Prev
    Next
    INDEX
    Explanations

    informal slang or non-standard language expressions

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

    Non-English character sequences

    np_acts-logits-general · gemini-2.0-flash

    technical terms and unicode errors

    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
     examples
    -0.89
     example
    -0.83
    Examples
    -0.72
    examples
    -0.69
     Examples
    -0.69
    example
    -0.67
     ejemplos
    -0.66
    例
    -0.64
     contoh
    -0.62
    Example
    -0.62
    POSITIVE LOGITS
    InjectAttribute
    1.06
    findpost
    0.99
     оригіналу
    0.98
     محفوظة
    0.95
    istoitu
    0.93
    UserScript
    0.92
     []:
    0.91
    GEBURTSDATUM
    0.89
     ModelExpression
    0.89
     дописавши
    0.88
    Activations Density 0.069%

    No Known Activations