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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1032
    Prev
    Next
    INDEX
    Explanations

    biological terms and references to specific proteins or molecular components

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

    abbreviations and acronyms, particularly those consisting of capital letters followed by periods or underscores.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     well
    -0.35
     cover
    -0.32
     подо
    -0.31
     St
    -0.30
     real
    -0.30
     star
    -0.28
     الع
    -0.28
     за
    -0.28
     fun
    -0.28
     starting
    -0.28
    POSITIVE LOGITS
    findpost
    0.77
    OGND
    0.67
    IVEREF
    0.62
     Walkover
    0.61
    المشاركات
    0.59
    Personensuche
    0.59
    richTextPanel
    0.59
     насељу
    0.59
    EndContext
    0.57
    BufferException
    0.57
    Activations Density 0.531%

    No Known Activations