© 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. 8137
    Prev
    Next
    INDEX
    Explanations

    key identifiers and relationships in complex statements or technical descriptions

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

    the word "second"

    np_acts-logits-general · gemini-2.0-flash

    second occurrence

    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
    WebVitals
    -0.63
    XmlEnum
    -0.53
    dafx
    -0.46
    gonic
    -0.45
    zzleHttp
    -0.45
    IVEREF
    -0.44
    Personendaten
    -0.44
     InputDecoration
    -0.43
    yntaxException
    -0.43
    Vidite
    -0.42
    POSITIVE LOGITS
     second
    3.65
    second
    3.25
    Second
    2.98
     Second
    2.83
     secondly
    2.75
     SECOND
    2.74
    SECOND
    2.62
     seconde
    2.52
     segunda
    2.51
     segundo
    2.51
    Activations Density 0.693%

    No Known Activations