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. 3-GEMMASCOPE-RES-16K
    6. 9506
    Prev
    Next
    INDEX
    Explanations

    instances of the word "survive" or its variations, indicating themes of survival or preservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ****************
    -0.63
     esp
    -0.59
     sou
    -0.58
     *$
    -0.58
    يو
    -0.57
    wendungs
    -0.56
     الق
    -0.56
    ial
    -0.56
    Bic
    -0.55
    dojo
    -0.55
    POSITIVE LOGITS
     survives
    2.47
     survive
    2.36
     survived
    2.33
     Survive
    2.07
    survi
    2.04
     surviving
    1.95
    Surviving
    1.86
     Survi
    1.82
     sobrevivir
    1.65
     sobrevi
    1.63
    Activations Density 0.085%

    No Known Activations