Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13965
    Prev
    Next
    INDEX
    Explanations

    technical terminology and expressions related to analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.18
    MemoryWarning
    -1.13
     Anſ
    -1.11
    ſelf
    -1.10
     Diſ
    -1.08
    rungsseite
    -1.08
    ſelves
    -1.05
     tartalomajánló
    -1.04
     Majefty
    -1.04
     ―――――
    -1.04
    POSITIVE LOGITS
    ↵
    0.71
     (
    0.69
     
    0.67
    …
    0.66
    ...
    0.65
    .
    0.64
     of
    0.64
     a
    0.63
     [
    0.62
    ↵↵
    0.62
    Activations Density 0.950%

    No Known Activations