Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3538
    Prev
    Next
    INDEX
    Explanations

    references to ceilings and related structural elements in a building

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    IsContent
    -0.52
     chrétien
    -0.45
    databind
    -0.44
     betweenstory
    -0.41
     kirj
    -0.41
    +#+#
    -0.41
     játék
    -0.40
     espectador
    -0.40
     volontaire
    -0.40
    galus
    -0.40
    POSITIVE LOGITS
     ceiling
    1.52
     Ceiling
    1.26
    ceiling
    1.25
     ceilings
    1.23
     roof
    1.20
    Ceiling
    1.18
     Roof
    1.04
    Roof
    1.02
    roof
    1.02
     ROOF
    0.99
    Activations Density 0.103%

    No Known Activations