© 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. 12858
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" in various contexts

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

    followed bywith respectwith incidencewith allwith properwith undifferentiatedwith both

    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
     queſta
    -0.64
    KURZBESCHREIBUNG
    -0.62
     MenuView
    -0.59
    orianCalendar
    -0.58
     mergeFrom
    -0.57
    ruptedException
    -0.56
    lapsingToolbar
    -0.54
    LayoutPanel
    -0.53
    MarshalTo
    -0.53
     MemoryStream
    -0.52
    POSITIVE LOGITS
     türlü
    0.43
    IfNeeded
    0.39
     adesivos
    0.38
     fallu
    0.37
     køb
    0.36
     evident
    0.36
    Referències
    0.35
     AssemblyTitle
    0.35
     intense
    0.35
    rxjs
    0.34
    Activations Density 0.046%

    No Known Activations