© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11182
    Prev
    Next
    INDEX
    Explanations

    technical terms related to weather and language processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.49
     ramp
    -0.42
     itſelf
    -0.41
     CWE
    -0.41
    MetaObject
    -0.40
     medically
    -0.39
    样的
    -0.38
    观的
    -0.38
     ſt
    -0.38
     referrerpolicy
    -0.37
    POSITIVE LOGITS
    didSet
    0.54
    ftagPool
    0.54
     surla
    0.53
    oredCriteria
    0.49
     esternos
    0.48
     utafitiHapana
    0.48
    новништво
    0.48
    Opportunities
    0.46
     orgánico
    0.46
     Kerja
    0.46
    Activations Density 0.019%

    No Known Activations