© 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. 15-GEMMASCOPE-RES-16K
    6. 4806
    Prev
    Next
    INDEX
    Explanations

    terms related to scaling and adjustments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.66
     Corbett
    -0.63
    Orsay
    -0.60
     Чита
    -0.59
    **/
    
    -0.58
     Padova
    -0.58
    Gemeinden
    -0.57
     Dempsey
    -0.57
    %%
    
    -0.57
    ()));
    
    -0.56
    POSITIVE LOGITS
     scales
    1.67
     Scales
    1.63
    Scales
    1.55
     Scale
    1.51
     SCALE
    1.51
    scales
    1.47
     scale
    1.45
    Scale
    1.41
    SCALE
    1.39
    scale
    1.27
    Activations Density 0.102%

    No Known Activations