Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1109
    Prev
    Next
    INDEX
    Explanations

    expressions of negation or refusal

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

    Contractions with "t" or the word "forget"

    np_acts-logits-general · gemini-2.0-flash

    "don't" followed by common verbs

    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
    zusetzen
    -0.42
     darte
    -0.40
    عي
    -0.40
     couverte
    -0.40
     recevrez
    -0.39
     consulté
    -0.39
    hal
    -0.39
     remporté
    -0.38
     mantend
    -0.38
     hebdomada
    -0.38
    POSITIVE LOGITS
     forget
    1.13
     worry
    0.86
     underestimate
    0.85
     misunderstand
    0.79
     onCancelled
    0.78
    forget
    0.77
    DJANGO
    0.74
     Forget
    0.74
    MultipartFile
    0.74
    Forget
    0.71
    Activations Density 0.061%

    No Known Activations