© 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. 14-GEMMASCOPE-RES-16K
    6. 2648
    Prev
    Next
    INDEX
    Explanations

    references to the concept of survival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marston
    -0.69
    #
    -0.68
    zeptember
    -0.66
    даго
    -0.65
    ⓧ
    -0.64
    ActionCreators
    -0.63
    Kus
    -0.62
     graines
    -0.61
    loma
    -0.61
    -£
    -0.59
    POSITIVE LOGITS
     survi
    1.45
     survive
    1.42
     survivors
    1.39
     Survi
    1.38
    survi
    1.38
     Survive
    1.37
     survives
    1.36
     survivor
    1.35
     Survivors
    1.30
    Survi
    1.30
    Activations Density 0.107%

    No Known Activations