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. 23-GEMMASCOPE-RES-16K
    6. 8936
    Prev
    Next
    INDEX
    Explanations

    comparative phrases involving "as" and "how"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.56
     Elsewhere
    -0.53
    enderror
    -0.51
     ois
    -0.51
    posedge
    -0.50
     InkWell
    -0.48
    PhysRevD
    -0.48
    ness
    -0.48
    ppuden
    -0.45
    riwal
    -0.45
    POSITIVE LOGITS
     many
    3.16
    many
    2.45
    Many
    2.27
     Many
    2.23
     MANY
    2.16
     muchos
    2.10
     muitos
    1.99
     vielen
    1.90
    MANY
    1.90
     viele
    1.89
    Activations Density 0.275%

    No Known Activations