© 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. 24-GEMMASCOPE-RES-16K
    6. 4769
    Prev
    Next
    INDEX
    Explanations

    escape sequences or escape characters within a programming context

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

    Newline character followed by a character

    np_acts-logits-general · gemini-2.0-flash

    end punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMPL
    -0.54
     click
    -0.54
     Rankin
    -0.54
    rungsseite
    -0.53
     ant
    -0.51
    IUS
    -0.50
    contentLoaded
    -0.50
    competent
    -0.50
     Cuevas
    -0.48
     anti
    -0.48
    POSITIVE LOGITS
    "\
    0.65
    !\
    0.65
     noqa
    0.64
    }^{-}\
    0.61
    StructEnd
    0.61
     "\
    0.58
     pregn
    0.56
    ?\
    0.55
     viewDidLoad
    0.55
    '\
    0.55
    Activations Density 0.097%

    No Known Activations