© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10827
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to communication and talking

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

    speech or responses

    np_acts-logits-general · gemini-2.0-flash

    say, says, said, yelling, votes

    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
    ')")
    -0.74
     contd
    -0.70
     ―――――
    -0.70
     ſind
    -0.69
     RSITY
    -0.67
     Diſ
    -0.66
     Efq
    -0.66
     Majefty
    -0.65
     $_"
    -0.65
     ――――――――
    -0.64
    POSITIVE LOGITS
     ‘
    1.40
     '
    1.33
     “
    1.06
     "
    1.05
     `
    0.96
     «
    0.93
     hey
    0.90
    『
    0.84
     \"
    0.83
     yes
    0.82
    Activations Density 0.391%

    No Known Activations