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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12579
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions that seek affirmation or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.53
    
    -0.48
     Савезне
    -0.45
    TestingModule
    -0.44
    gameserver
    -0.43
    HasAnnotation
    -0.41
    ngilizce
    -0.39
    detalles
    -0.39
    hlin
    -0.38
    siers
    -0.38
    POSITIVE LOGITS
    offsetof
    0.47
     &___
    0.43
     HFILL
    0.41
     huh
    0.41
     endforeach
    0.41
    ませんか
    0.40
     snippetHide
    0.40
    是吗
    0.40
    appellant
    0.40
    Javadoc
    0.39
    Activations Density 0.110%

    No Known Activations