Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2645
    Prev
    Next
    INDEX
    Explanations

    terms related to monitoring and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     słucha
    -0.49
     intptr
    -0.48
     suprême
    -0.44
    esercito
    -0.44
     współpracy
    -0.43
     čier
    -0.42
     przeznac
    -0.41
    explique
    -0.41
     zwykle
    -0.39
     téléph
    -0.39
    POSITIVE LOGITS
     pattern
    0.90
     profile
    0.83
    spot
    0.77
     plot
    0.73
     profiles
    0.72
    yy
    0.72
     patterns
    0.69
     monitoring
    0.67
    pattern
    0.65
     spot
    0.63
    Activations Density 0.641%

    No Known Activations