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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7994
    Prev
    Next
    INDEX
    Explanations

    references to volume measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Hadd
    -0.75
     tensile
    -0.67
     dAtA
    -0.67
    @",
    -0.64
    Quelles
    -0.63
    Twas
    -0.63
    +#+
    -0.63
     Barclay
    -0.62
     tendons
    -0.60
     Tensile
    -0.59
    POSITIVE LOGITS
     volumes
    1.67
     volume
    1.63
     Volume
    1.58
    volume
    1.53
    volumes
    1.50
     Volumes
    1.50
     VOLUME
    1.49
    Volume
    1.46
    Volumes
    1.43
    VOLUME
    1.39
    Activations Density 0.060%

    No Known Activations