© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 50699
    Prev
    Next
    INDEX
    Explanations

    PHP opening tags and templating syntax used in web development

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

    template syntax and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.64
    onShow
    -0.61
     Simpli
    -0.57
    ExtendWith
    -0.57
     nb
    -0.56
     Tind
    -0.53
    JSONException
    -0.52
     SCOPE
    -0.50
    XA
    -0.50
     Xn
    -0.50
    POSITIVE LOGITS
    ="<?
    0.80
    ="{{
    0.80
    ="{{$
    0.60
    ="<?=
    0.59
    ="'
    0.57
    ="${
    0.55
    endsection
    0.51
    !("{
    0.51
    ="'+
    0.50
    ="../../
    0.50
    Activations Density 0.009%

    No Known Activations