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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6458
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "ob-" in various forms

    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
    @[+][
    -0.62
     HasFactory
    -0.59
     EdgeInsets
    -0.56
    География
    -0.55
    Trayectoria
    -0.55
    principalColumn
    -0.54
    classnames
    -0.54
    期刊论文
    -0.53
    ◗
    -0.53
     externi
    -0.53
    POSITIVE LOGITS
     Ob
    0.82
    Ob
    0.62
     OB
    0.61
     ob
    0.59
     Obs
    0.58
     calendriers
    0.57
     obs
    0.56
    obs
    0.55
     OBJ
    0.55
     Obst
    0.54
    Activations Density 0.104%

    No Known Activations