© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11207
    Prev
    Next
    INDEX
    Explanations

    questions and concerns related to code functionality and performance issues

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

    a problem, question, or a "missing" element

    np_acts-logits-general · gemini-2.0-flash

    here, useful, issues, detail, flags, memory

    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
    tonode
    -0.74
    Hentet
    -0.73
    ContentAsync
    -0.70
    WebControls
    -0.70
    IntoConstraints
    -0.68
     jScrollPane
    -0.65
    enumii
    -0.65
     Roskov
    -0.62
    сылкі
    -0.59
    ::_('
    -0.59
    POSITIVE LOGITS
     here
    2.92
    here
    2.16
     aquí
    2.11
     aici
    2.09
     здесь
    2.02
     disini
    1.92
     هنا
    1.90
    Here
    1.90
     Here
    1.87
     ici
    1.86
    Activations Density 0.630%

    No Known Activations