© 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. 909
    Prev
    Next
    INDEX
    Explanations

    questions and statements regarding factors or multiples

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

    True or False statements

    np_acts-logits-general · gemini-2.0-flash

    neither wed nor unwed

    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
    دانشنامهٔ
    -0.71
    =$?
    -0.67
    Hozzáférés
    -0.66
    شهاد
    -0.64
    setof
    -0.63
     متعلقه
    -0.63
     &___
    -0.62
     jScrollPane
    -0.60
    ONSORED
    -0.59
    ISupport
    -0.59
    POSITIVE LOGITS
     neither
    0.87
     less
    0.72
     наоборот
    0.66
     Neither
    0.64
    Neither
    0.63
    neither
    0.60
    逆に
    0.56
     menos
    0.56
    less
    0.56
     hingegen
    0.55
    Activations Density 1.923%

    No Known Activations