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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3236
    Prev
    Next
    INDEX
    Explanations

    code snippets that define properties and methods in C#

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

    C# properties with get and set accessors

    np_acts-logits-general · gemini-2.0-flash

    C# get properties

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     purpoſe
    -0.46
    MLLoader
    -0.44
    migrationBuilder
    -0.44
     ſche
    -0.42
    sság
    -0.41
    cías
    -0.39
    gangssprach
    -0.38
    }(),
    -0.38
    enderror
    -0.38
    pantalón
    -0.38
    POSITIVE LOGITS
    новништво
    0.56
     @"/
    0.54
     كومونز
    0.51
     فريبيس
    0.50
    MENAFN
    0.49
     AssemblyVersion
    0.49
    VIAF
    0.48
    DockStyle
    0.47
     насељу
    0.47
     VIAF
    0.44
    Activations Density 0.089%

    No Known Activations