© 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. 18-GEMMASCOPE-RES-16K
    11. 11125
    Prev
    Next
    INDEX
    Explanations

    noteworthy information and updates, particularly in the form of notes

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

    Text after "Note" or "NOTE"

    np_acts-logits-general · gemini-2.0-flash

    note: or edit: leading explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -1.33
    Попис
    -1.06
    NUMX
    -1.05
     насељу
    -1.02
     AssemblyVersion
    -0.97
    tagext
    -0.95
    bewerken
    -0.94
    >");
    -0.90
    AddTagHelper
    -0.90
    ,:);
    -0.89
    POSITIVE LOGITS
    :
    1.01
    !
    0.65
     Although
    0.55
     This
    0.53
    !!!
    0.53
     If
    0.52
    !!
    0.52
     There
    0.52
    Although
    0.51
    **
    0.51
    Activations Density 0.189%

    No Known Activations