© 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. 18-GEMMASCOPE-RES-16K
    11. 14201
    Prev
    Next
    INDEX
    Explanations

    dialogue or quotations within the text

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

    Comes after periods, quotes, or certain words

    np_acts-logits-general · gemini-2.0-flash

    imaging, dotted, punctuation

    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
    
    -0.94
     متعلقه
    -0.94
    principalColumn
    -0.86
     defaultstate
    -0.84
     initComponents
    -0.83
    Lähteet
    -0.82
    WebElementEntity
    -0.76
    ">//
    -0.74
     تانيه
    -0.73
     MonoBehaviour
    -0.73
    POSITIVE LOGITS
    Reach
    0.48
     Reach
    0.46
     l
    0.43
     contra
    0.42
    ↵↵
    0.42
    ■
    0.41
     Staff
    0.40
    メール
    0.40
    jm
    0.39
     برانيه
    0.39
    Activations Density 0.060%

    No Known Activations