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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3305
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to digital technology and its applications

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

    that can be proper nouns or parts of proper nouns

    np_acts-logits-general · gemini-2.0-flash

    assassin, State, mechatronics, Leviticus, sequestration, gel, strobe, ROC

    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
    withOpacity
    -0.58
    +#+#
    -0.54
     AssemblyTitle
    -0.52
    principalColumn
    -0.51
    期刊论文
    -0.50
     дописавши
    -0.50
     NSCoder
    -0.48
    migrationBuilder
    -0.48
    PhysRev
    -0.48
     calendriers
    -0.47
    POSITIVE LOGITS
     fatiga
    0.47
    StoryboardSegue
    0.46
     ComVisible
    0.46
    Contours
    0.45
    BoxShadow
    0.43
     AssemblyCulture
    0.42
     informée
    0.42
    xtures
    0.42
     gynhyrchwyd
    0.42
    PACS
    0.41
    Activations Density 1.761%

    No Known Activations