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. 124729
    Prev
    Next
    INDEX
    Explanations

    measurements and distances related to trails and paths

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

    measurement of distance

    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
     InputDecoration
    -0.40
    ungsbedingungen
    -0.40
    ImageIO
    -0.37
    住
    -0.36
    CreateModel
    -0.36
     sécher
    -0.36
     EconPapers
    -0.36
    WireFormatLite
    -0.35
    security
    -0.35
     $__
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.71
     صوتيه
    0.59
    ChildScrollView
    0.58
     ujednoznacz
    0.50
     برانيه
    0.47
    tanleria
    0.47
     longueur
    0.47
     mobilization
    0.46
     lenght
    0.46
     Panjang
    0.46
    Activations Density 0.021%

    No Known Activations