© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating obligation or expectation

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

    preceding "to" that indicate obligation/likelihood

    np_acts-logits-general · gemini-2.0-flash

    modal verb + to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.97
    astify
    -0.96
    SourceChecksum
    -0.83
     resourceCulture
    -0.83
    Bioaccumulative
    -0.79
    XmlIgnore
    -0.76
    IsMutable
    -0.76
    PreferredItem
    -0.74
    ]--;
    -0.74
    TypedDataSet
    -0.74
    POSITIVE LOGITS
     to
    1.93
    to
    0.74
     να
    0.72
     să
    0.59
     einz
    0.58
     להת
    0.56
    ToAdd
    0.55
    ารถ
    0.53
     fallu
    0.53
     להשת
    0.53
    Activations Density 0.693%

    No Known Activations