© 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. 10-GEMMASCOPE-RES-16K
    6. 15542
    Prev
    Next
    INDEX
    Explanations

    conclusory phrases or summarizing statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rokken
    -0.58
     pourtant
    -0.56
    itchfield
    -0.54
    model
    -0.53
     Sociales
    -0.50
     actionBar
    -0.49
    %)$
    -0.49
    truction
    -0.48
    untura
    -0.47
    porus
    -0.47
    POSITIVE LOGITS
     Lastly
    0.98
     lastly
    0.95
    Lastly
    0.95
     Finally
    0.88
    Finally
    0.87
     ostavi
    0.86
    Obrázky
    0.85
    Personendaten
    0.81
     finally
    0.81
    finally
    0.78
    Activations Density 0.162%

    No Known Activations