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. 2-GEMMASCOPE-RES-16K
    6. 4750
    Prev
    Next
    INDEX
    Explanations

    expressions of preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Έ
    -0.53
     स
    -0.51
     benar
    -0.51
    ↵↵↵
    -0.49
    端
    -0.49
    ↵
    -0.49
     Tre
    -0.48
    glycemia
    -0.47
     permission
    -0.47
    Parcelable
    -0.47
    POSITIVE LOGITS
     prefer
    2.60
     preferred
    2.53
    preferred
    2.48
     prefers
    2.38
     Prefer
    2.36
    prefer
    2.34
     Preferred
    2.33
     preferring
    2.18
    Preferred
    2.12
    Prefer
    2.10
    Activations Density 0.076%

    No Known Activations