© 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. 22-GEMMASCOPE-RES-16K
    11. 3124
    Prev
    Next
    INDEX
    Explanations

    discussions about political norms and the consequences of violating them

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

    Followed by commas or periods after specific words

    np_acts-logits-general · gemini-2.0-flash

    punctuation and breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -0.94
    Whilst
    -0.92
     Whilst
    -0.92
     welche
    -0.91
     didalam
    -0.88
    luß
    -0.88
     welches
    -0.86
     אשר
    -0.84
     diantaranya
    -0.84
     می‌باشد
    -0.82
    POSITIVE LOGITS
    ​—
    1.05
    —“
    0.98
    —"
    0.86
    —
    0.79
    —”
    0.76
     —
    0.72
     —
    0.68
    ”—
    0.66
    --"
    0.65
    )—
    0.65
    Activations Density 2.132%

    No Known Activations