© 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. 23-GEMMASCOPE-RES-16K
    6. 11012
    Prev
    Next
    INDEX
    Explanations

    negations or words expressing a lack or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     not
    -0.64
     already
    -0.62
     likewise
    -0.60
     also
    -0.55
     sudah
    -0.54
     still
    -0.53
     efectivamente
    -0.53
     tidak
    -0.49
    already
    -0.49
    still
    -0.48
    POSITIVE LOGITS
    rawDesc
    0.66
     esternos
    0.65
    AddTagHelper
    0.65
    ."</
    0.63
    bewerken
    0.62
    İstinadlar
    0.61
    Skocz
    0.61
    tanleria
    0.60
    vias
    0.59
     ?>/
    0.59
    Activations Density 0.039%

    No Known Activations