© 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. 396
    Prev
    Next
    INDEX
    Explanations

    instructions and commands related to debugging and navigating software interfaces

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

    Keyboard input and control keys

    np_acts-logits-general · gemini-2.0-flash

    keyboard shortcuts

    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
    empio
    -0.47
    脚注の使い方
    -0.46
    SourceChecksum
    -0.44
     "<?
    -0.41
     språk
    -0.41
     مرئيه
    -0.41
    findpost
    -0.40
    dene
    -0.38
     zicht
    -0.38
     Participating
    -0.37
    POSITIVE LOGITS
     keys
    1.24
    Press
    1.16
     Press
    1.16
    KEYCODE
    1.15
     press
    1.15
     keyboard
    1.15
     pressed
    1.11
     key
    1.09
     pressing
    1.08
     Keys
    1.08
    Activations Density 0.263%

    No Known Activations