© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    indications of user engagement or calls to action

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

    references to interactive content or navigation prompts

    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
    -
    -0.48
    velocityX
    -0.45
    .
    -0.45
    es
    -0.43
    we
    -0.43
    state
    -0.43
     (
    -0.42
    …
    -0.42
    3
    -0.41
    –
    -0.41
    POSITIVE LOGITS
     مشين
    1.13
    MemoryWarning
    1.12
     дописавши
    1.10
    WebVitals
    1.07
    
    1.05
     виправивши
    1.04
    Datuak
    1.03
     typelib
    0.99
     bezeichneter
    0.98
    تقاوى
    0.97
    Activations Density 0.055%

    No Known Activations