© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 2812
    Prev
    Next
    INDEX
    Explanations

    phrases expressing conditions or possibilities related to preferences

    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
     oprot
    -0.41
    帖最后由
    -0.39
    Ответить
    -0.37
    strSql
    -0.37
     AttributeSet
    -0.37
    ChildScrollView
    -0.36
    rungsseite
    -0.36
    icted
    -0.36
    ulipas
    -0.36
    writerow
    -0.35
    POSITIVE LOGITS
     CanadaChoose
    0.49
     neceſſ
    0.49
     advantageous
    0.47
     awesome
    0.47
    awtextra
    0.45
    /**
    0.45
     Numerade
    0.44
     OK
    0.44
     pleaſure
    0.43
     nice
    0.43
    Activations Density 0.657%

    No Known Activations