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. 37-GEMMASCOPE-RES-16K
    6. 4524
    Prev
    Next
    INDEX
    Explanations

    terms related to distribution and dissemination of resources or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sumpay
    -0.47
    تقاوى
    -0.42
     Photocase
    -0.41
    ografija
    -0.40
    帖最后由
    -0.40
    \{\\
    -0.39
    esModule
    -0.38
    tanleria
    -0.38
     مشين
    -0.38
    gestone
    -0.38
    POSITIVE LOGITS
     distribution
    3.58
     distribute
    3.30
     Distribution
    3.25
     distributing
    3.22
     distribu
    3.06
     distributes
    3.05
     distributions
    3.05
    distribution
    3.03
    Distribution
    3.02
     distributed
    3.00
    Activations Density 0.923%

    No Known Activations