© 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. 10811
    Prev
    Next
    INDEX
    Explanations

    contractions and informal phrases commonly used in conversational English

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

    Follows "let's", "let us", or "suppose"

    np_acts-logits-general · gemini-2.0-flash

    introducing suggestions or hypotheticals

    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
     <<<<<<<<<<<<<<
    -0.75
     Signalez
    -0.74
     المعيارى
    -0.72
     صوتيه
    -0.72
     OnTrigger
    -0.71
     pinulongan
    -0.70
    WireFormatLite
    -0.68
    OGND
    -0.68
     snippetHide
    -0.68
     pageContext
    -0.67
    POSITIVE LOGITS
     assume
    0.74
     face
    0.71
     suppose
    0.68
     imagine
    0.64
     us
    0.63
     pretend
    0.63
     say
    0.63
    Lets
    0.62
     talk
    0.60
     see
    0.59
    Activations Density 0.061%

    No Known Activations