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. 6774
    Prev
    Next
    INDEX
    Explanations

    phrases expressing problems or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "is" followed by "that" or "it"

    np_acts-logits-general · gemini-2.0-flash

    the problem is

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    GEBURTS
    -0.51
    OGND
    -0.41
     slov
    -0.35
    帖最后由
    -0.34
    getLogger
    -0.34
    νώ
    -0.33
     chi̍t
    -0.32
     başar
    -0.32
     célébr
    -0.32
    锈钢
    -0.32
    POSITIVE LOGITS
    AddHtmlAttribute
    0.58
    ulement
    0.51
     inconvenient
    0.50
    erdings
    0.50
     problemet
    0.47
    好在
    0.46
    偏偏
    0.46
     CURIAM
    0.46
     PROBLEM
    0.46
     probleem
    0.46
    Activations Density 0.276%

    No Known Activations