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. 18-GEMMASCOPE-RES-16K
    6. 10014
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure, particularly focusing on function definitions and control flow statements

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

    Code or non-English text

    np_acts-logits-general · gemini-2.0-flash

    w. followed by text

    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
    ChildScrollView
    -0.64
     normaux
    -0.58
     jScrollPane
    -0.55
     past
    -0.55
     Past
    -0.54
     confronti
    -0.51
    Past
    -0.50
     &___
    -0.50
     <=",
    -0.50
    AndEndTag
    -0.48
    POSITIVE LOGITS
    SOUNDBITE
    0.67
    Hentet
    0.56
    BeginContext
    0.55
    Autoritní
    0.54
     UIAlert
    0.53
     labour
    0.52
    reactstrap
    0.52
    Controllo
    0.52
     gyhoeddwyd
    0.51
    theless
    0.51
    Activations Density 0.015%

    No Known Activations