© 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. 2-GEMMASCOPE-RES-16K
    11. 12779
    Prev
    Next
    INDEX
    Explanations

    references to mice in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFICATE
    -0.47
     catch
    -0.40
    ErrUnexpectedEOF
    -0.39
     Lebe
    -0.39
     threatens
    -0.39
    +#+
    -0.39
    vum
    -0.38
    bitField
    -0.38
     betroffen
    -0.37
     Salter
    -0.37
    POSITIVE LOGITS
     Mice
    0.84
    Mice
    0.81
     mice
    0.80
    mice
    0.74
     piano
    0.72
    Piano
    0.69
     Piano
    0.68
    piano
    0.68
     Analyst
    0.65
    slave
    0.63
    Activations Density 0.373%

    No Known Activations