© 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. 2-GEMMASCOPE-RES-16K
    6. 8878
    Prev
    Next
    INDEX
    Explanations

    words related to selection in data or user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     absence
    -0.43
    发表于
    -0.36
     FileNotFound
    -0.35
    OGND
    -0.35
     duty
    -0.35
     dark
    -0.35
    ьаж
    -0.34
     gelap
    -0.34
    thenReturn
    -0.34
     cheap
    -0.33
    POSITIVE LOGITS
    select
    0.70
    selected
    0.59
    GPC
    0.58
    Datuak
    0.57
     Respond
    0.56
     continúas
    0.54
    Respond
    0.51
    ########.
    0.51
    lorette
    0.50
     hochzeit
    0.49
    Activations Density 0.118%

    No Known Activations