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. 103659
    Prev
    Next
    INDEX
    Explanations

    active verbs related to production or the process of making something

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

    action verbs

    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
     péri
    -0.38
    toBeDefined
    -0.35
    TouchableOpacity
    -0.34
     enrique
    -0.32
    Datei
    -0.32
     vacances
    -0.32
     buhay
    -0.32
     plastique
    -0.32
     dynamique
    -0.32
     تكبرها
    -0.31
    POSITIVE LOGITS
     незавершена
    0.82
     Normdatei
    0.67
    ConstraintMaker
    0.63
     beginnetje
    0.60
    Personensuche
    0.59
    TagMode
    0.59
    الحياه
    0.58
     שוליים
    0.55
    MarshalTo
    0.54
    #+#
    0.54
    Activations Density 0.306%

    No Known Activations