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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14432
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating capability or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after an auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    modal verbs starting questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.97
     Audiodateien
    -0.94
    UIControlState
    -0.88
    Portale
    -0.88
    noopener
    -0.85
    Попис
    -0.82
    Diwedd
    -0.81
     Infórmanos
    -0.80
     Roskov
    -0.79
    )++;
    -0.78
    POSITIVE LOGITS
     anyone
    0.65
    anyone
    0.59
     anybody
    0.56
     they
    0.53
     you
    0.52
    Anyone
    0.51
     there
    0.51
     someone
    0.49
     we
    0.48
     it
    0.47
    Activations Density 0.177%

    No Known Activations