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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8547
    Prev
    Next
    INDEX
    Explanations

    references to the absence or lack of something, particularly "no" or "any"

    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
    ?
    -0.53
    ,
    -0.52
    :
    -0.49
    <bos>
    -0.48
     to
    -0.45
    -0.45
    .
    -0.45
    ↵
    -0.44
     on
    -0.43
    M
    -0.42
    POSITIVE LOGITS
     myſelf
    1.38
     Efq
    1.29
     Theſe
    1.27
     ſche
    1.25
     pleaſure
    1.24
     Beſ
    1.23
     perfons
    1.20
     مشين
    1.19
     ſeveral
    1.18
     purpoſe
    1.17
    Activations Density 0.587%

    No Known Activations