© 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. 118592
    Prev
    Next
    INDEX
    Explanations

    terms related to fluid entry and exit points in systems

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

    inflow and inlet points

    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
    CppMethod
    -0.59
    onOptions
    -0.57
    stdbool
    -0.56
    RTEE
    -0.56
     disambiguazione
    -0.54
     MonoBehaviour
    -0.54
     المعيارى
    -0.53
     antiqu
    -0.52
    webElementXpaths
    -0.52
    IBAction
    -0.52
    POSITIVE LOGITS
     Inlet
    1.90
     inlet
    1.90
     inlets
    1.44
    entrance
    0.77
     entrance
    0.73
    Outlet
    0.70
     Entrance
    0.69
     Entry
    0.66
    entry
    0.66
    outlet
    0.64
    Activations Density 0.009%

    No Known Activations