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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14819
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    OGND
    -0.65
    Datuak
    -0.59
     الرياضيه
    -0.57
    delwed
    -0.54
     noDo
    -0.53
    يميديا
    -0.52
    WebElementEntity
    -0.51
     SwitchCompat
    -0.51
    LookAnd
    -0.50
    mybatisplus
    -0.50
    POSITIVE LOGITS
     seems
    0.77
     apparently
    0.72
     seem
    0.71
     scheint
    0.68
     Seems
    0.67
    Apparently
    0.66
    seems
    0.65
    Seems
    0.64
     Apparently
    0.64
     scheinen
    0.63
    Activations Density 0.541%

    No Known Activations