© 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. 24-GEMMASCOPE-RES-16K
    11. 8439
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "approach" or related terms in a technical context

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

    starting with "Appro" or "Bas"

    np_acts-logits-general · gemini-2.0-flash

    approvals and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.62
    zzlies
    -0.61
     BrowserModule
    -0.57
    jzen
    -0.57
    postmedia
    -0.56
    tonsoft
    -0.56
    ########.
    -0.55
    MetaObject
    -0.55
    omeness
    -0.55
    mester
    -0.54
    POSITIVE LOGITS
    Portail
    0.51
    complexType
    0.46
    mat
    0.41
     mat
    0.40
     jScrollPane
    0.40
    devamını
    0.39
    mill
    0.39
    CO
    0.39
     जन
    0.39
    філь
    0.39
    Activations Density 0.682%

    No Known Activations