© 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. 22-GEMMASCOPE-RES-16K
    11. 13558
    Prev
    Next
    INDEX
    Explanations

    references to the term "Hol" or variations related to it, which may signify specific entities or concepts associated with that term

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

    'hol' followed by 'enstein' or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    hol, bol followed by enstein or stered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.78
    MENAFN
    -0.61
    BeginContext
    -0.59
    Personendaten
    -0.58
    TabIndex
    -0.58
    CodeAttribute
    -0.55
    습니다
    -0.54
    principalColumn
    -0.54
    esgue
    -0.54
    NGC
    -0.53
    POSITIVE LOGITS
     Jol
    0.53
    scriptcase
    0.50
    ValueStyle
    0.49
    bol
    0.48
     Coaster
    0.48
    LElement
    0.47
     hairline
    0.45
    TemporalType
    0.45
     battre
    0.45
     kasarigan
    0.45
    Activations Density 0.140%

    No Known Activations