© 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. 3992
    Prev
    Next
    INDEX
    Explanations

    references to transformations and abilities of characters in fantastical contexts

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

    appearance or transformation

    np_acts-logits-general · gemini-2.0-flash

    appearance and transformation

    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
    OrNil
    -0.44
    $_['
    -0.42
    adhé
    -0.41
     грамо
    -0.41
     code
    -0.41
     iprot
    -0.40
    तिहास
    -0.40
    PendingIntent
    -0.39
    有效
    -0.39
    سكري
    -0.39
    POSITIVE LOGITS
     likeness
    1.10
     visage
    1.04
     appearance
    1.04
     facial
    1.03
     resemblance
    1.01
     Appearance
    0.99
     Face
    0.96
     ressemb
    0.95
     face
    0.94
     transformations
    0.94
    Activations Density 0.359%

    No Known Activations