© 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. 2915
    Prev
    Next
    INDEX
    Explanations

    specific characteristics and features related to product descriptions, particularly focusing on quality, material, and design attributes

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

    Parts of objects

    np_acts-logits-general · gemini-2.0-flash

    parts and components

    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
    EndContext
    -0.62
    BeginContext
    -0.55
    قایناق‌لار
    -0.54
    ⓧ
    -0.53
     doInBackground
    -0.47
    Engines
    -0.46
     Técnica
    -0.45
    JFrame
    -0.45
    !*\
    -0.45
     rooms
    -0.45
    POSITIVE LOGITS
     intégrée
    0.64
     safety
    0.62
     vertes
    0.61
    apimachinery
    0.60
    knob
    0.58
     Himo
    0.58
     clips
    0.58
     lisse
    0.57
     knob
    0.57
     knobs
    0.57
    Activations Density 0.246%

    No Known Activations