© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4647
    Prev
    Next
    INDEX
    Explanations

    references to specific variables or identifiers related to configuration or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    K and chan references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AdapterView
    -0.51
     Initialized
    -0.40
    BASEPATH
    -0.38
    Proposals
    -0.38
    lectro
    -0.37
    campista
    -0.37
    evt
    -0.36
    TabStop
    -0.36
    Wrk
    -0.35
    skon
    -0.35
    POSITIVE LOGITS
     UHD
    0.81
     uhd
    0.66
     noqa
    0.63
    高清
    0.63
     HD
    0.60
     hd
    0.54
    Personensuche
    0.53
     高清
    0.50
    rizona
    0.48
    SourceChecksum
    0.47
    Activations Density 0.009%

    No Known Activations