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. 17-GEMMASCOPE-RES-16K
    6. 10975
    Prev
    Next
    INDEX
    Explanations

    phrases related to risk and preventative measures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̈́
    -0.56
     تقری
    -0.55
     praticamente
    -0.53
     trier
    -0.52
    HideFlags
    -0.51
    WriteBarrier
    -0.51
    almost
    -0.50
    assertNotNull
    -0.50
    RTLR
    -0.50
    WarningLevel
    -0.50
    POSITIVE LOGITS
    万一
    0.89
    到时候
    0.80
     accidentally
    0.77
     allzu
    0.74
     too
    0.73
     inadvertently
    0.70
     يتيمه
    0.70
     potentially
    0.67
     nanti
    0.66
    DockStyle
    0.63
    Activations Density 0.400%

    No Known Activations