© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    references to various aspects and types of freedom

    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
    rungsseite
    -0.84
    WebElementEntity
    -0.77
    Kanpo
    -0.71
     Mortar
    -0.69
     briefcase
    -0.69
    pearance
    -0.69
     Meld
    -0.69
    ității
    -0.69
    chism
    -0.68
    oneph
    -0.68
    POSITIVE LOGITS
     freedom
    1.76
     Freedom
    1.70
    Freedom
    1.60
    freedom
    1.49
     FREEDOM
    1.49
     freedoms
    1.35
     free
    1.21
     liberty
    1.20
     freed
    1.20
     Free
    1.20
    Activations Density 0.088%

    No Known Activations