© 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. 33-GEMMASCOPE-RES-16K
    6. 7638
    Prev
    Next
    INDEX
    Explanations

    references to the variable 'Q' and its associated data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.49
    Derbyniad
    -0.47
    Архівовано
    -0.45
    TargetException
    -0.43
     الرياضيه
    -0.42
    ChildScrollView
    -0.42
     CanadaChoose
    -0.40
    datei
    -0.40
    mirante
    -0.40
    Personendaten
    -0.40
    POSITIVE LOGITS
     Q
    0.55
     Tarantino
    0.49
    riceps
    0.45
    tionnaire
    0.45
     q
    0.44
    delwed
    0.43
     literally
    0.42
     ſind
    0.42
     bq
    0.41
    addafi
    0.40
    Activations Density 0.656%

    No Known Activations