© 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. 5-GEMMASCOPE-RES-16K
    6. 7879
    Prev
    Next
    INDEX
    Explanations

    references to fingers and their interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Machado
    -0.65
    țele
    -0.63
    abetes
    -0.61
    ിക
    -0.60
    lognese
    -0.60
     betweenstory
    -0.56
     W
    -0.55
    ţele
    -0.55
    CLAIMER
    -0.55
     хло
    -0.55
    POSITIVE LOGITS
     Finger
    1.40
     finger
    1.39
    Finger
    1.28
     fingers
    1.26
    finger
    1.25
     Fingers
    1.09
     Poverty
    1.07
    fingers
    1.00
     Tind
    0.98
    Datuak
    0.96
    Activations Density 0.116%

    No Known Activations