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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6529
    Prev
    Next
    INDEX
    Explanations

    terms related to synthesis and adaptation in biological or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.53
     kere
    -0.51
     big
    -0.49
    Krok
    -0.47
     Linder
    -0.47
     interno
    -0.47
     createSlice
    -0.45
     références
    -0.45
     लेकर
    -0.45
     JpaRepository
    -0.44
    POSITIVE LOGITS
    ſelf
    1.08
     Jefus
    1.03
    ſelves
    1.00
     Efq
    0.93
     Majefty
    0.93
     ſind
    0.92
     himſelf
    0.90
     ſy
    0.89
     raiſ
    0.88
     neceff
    0.88
    Activations Density 0.635%

    No Known Activations