© 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. 17-GEMMASCOPE-RES-16K
    6. 12927
    Prev
    Next
    INDEX
    Explanations

    instances of hanging or suspension narratives

    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
    PageIndex
    -0.56
     Abp
    -0.53
    Abp
    -0.53
    éez
    -0.42
     thức
    -0.42
     Shun
    -0.42
    blit
    -0.42
     Betten
    -0.41
    lito
    -0.40
     wedge
    -0.40
    POSITIVE LOGITS
     hanging
    1.39
     hangs
    1.34
     hung
    1.34
     HANG
    1.31
     hang
    1.30
     Hanging
    1.29
     hanged
    1.29
    hanging
    1.24
    Hanging
    1.23
     Hang
    1.22
    Activations Density 0.219%

    No Known Activations