Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4604
    Prev
    Next
    INDEX
    Explanations

    phrases expressing concerns about life and existential anxiety

    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
    /');
    -0.69
    Nope
    -0.59
     incentiv
    -0.57
     gynhyrchwyd
    -0.56
    /')
    -0.55
    tagHelperRunner
    -0.55
    !)
    -0.55
    ed
    -0.55
     \%-
    -0.54
    ilha
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    0.74
     الحره
    0.73
     חיצוניים
    0.73
    Lähteet
    0.67
    Filmographie
    0.66
    userdetails
    0.62
    extAlignment
    0.58
    IBar
    0.58
    ]")]
    0.58
     odkazy
    0.56
    Activations Density 0.091%

    No Known Activations