© 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. 25-GEMMASCOPE-RES-16K
    6. 12650
    Prev
    Next
    INDEX
    Explanations

    promotions and offers related to online gambling or casino games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.61
     LIABILITY
    -0.53
    Παραπομπές
    -0.50
     TestBed
    -0.49
     оригіналу
    -0.47
    BeginContext
    -0.47
    Personendaten
    -0.45
    فایل‌لار
    -0.45
    "><!--
    -0.45
    tache
    -0.45
    POSITIVE LOGITS
    RetentionPolicy
    0.73
    ImageField
    0.53
     nuo
    0.51
    LookAnd
    0.48
    LLocation
    0.48
    EditorBrowsable
    0.47
    kirchen
    0.46
     lus
    0.46
     auri
    0.46
     arred
    0.45
    Activations Density 0.077%

    No Known Activations