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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 97783
    Prev
    Next
    INDEX
    Explanations

    references to Visual Studio (VS) and related software terms

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

    VS or vs

    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
    Redirection
    -0.47
     aDecoder
    -0.47
    upuncture
    -0.44
    Luxembourg
    -0.43
    odendron
    -0.43
    artement
    -0.42
    reonine
    -0.41
    CAPÍTULO
    -0.41
    earch
    -0.41
    ruptedException
    -0.40
    POSITIVE LOGITS
    vs
    2.48
    VS
    2.47
     VS
    2.39
     vs
    2.13
     Vs
    1.98
    Vs
    1.82
     Versus
    1.68
    versus
    1.68
     versus
    1.63
    Versus
    1.57
    Activations Density 0.018%

    No Known Activations