© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9993
    Prev
    Next
    INDEX
    Explanations

    themes related to danger and threat posed by various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.48
     resourceCulture
    -0.44
    pushFollow
    -0.43
    numerusform
    -0.42
     helping
    -0.39
    Letting
    -0.38
     váll
    -0.38
     przyzna
    -0.38
    Help
    -0.37
     letting
    -0.37
    POSITIVE LOGITS
     steals
    0.66
     exploiting
    0.63
     stole
    0.62
     kasarigan
    0.62
     steal
    0.60
     threatens
    0.59
     threaten
    0.59
     threatening
    0.57
     exploit
    0.55
     unchecked
    0.53
    Activations Density 0.712%

    No Known Activations