© 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. 24-GEMMASCOPE-RES-16K
    11. 12608
    Prev
    Next
    INDEX
    Explanations

    terms related to future prospects and challenges in various contexts

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

    before periods or commas

    np_acts-logits-general · gemini-2.0-flash

    end of statement or quote

    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
    UCION
    -0.65
     swat
    -0.59
    ITECT
    -0.58
    lexia
    -0.57
    fuge
    -0.56
    imeo
    -0.55
    PAIGN
    -0.55
    ALIAN
    -0.54
    ESOME
    -0.54
    rosia
    -0.53
    POSITIVE LOGITS
    ?")
    1.73
    ")
    1.60
    ?");
    1.59
    ?"
    1.55
    !")
    1.55
    ?')
    1.55
    ?”
    1.54
    ?)
    1.54
    ),”
    1.52
    "))
    1.47
    Activations Density 3.697%

    No Known Activations