© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 2442
    Prev
    Next
    INDEX
    Explanations

    expressions indicating doubt or questioning belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.47
    Datuak
    -0.44
    StoryboardSegue
    -0.44
     ब्रेकडाउन
    -0.42
    Identyfik
    -0.38
     يتيمه
    -0.37
     Inſ
    -0.37
     كورة
    -0.36
    фициальный
    -0.36
    rician
    -0.35
    POSITIVE LOGITS
     believe
    2.81
     belief
    2.52
    believe
    2.41
     believing
    2.39
     Believe
    2.36
     believes
    2.31
    Believe
    2.30
     believed
    2.22
     Belief
    2.20
     BELIEVE
    2.19
    Activations Density 0.586%

    No Known Activations