Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11036
    Prev
    Next
    INDEX
    Explanations

    terms related to consumer rights and regulations regarding credit reports and disclosures

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

    Credit or criminal background

    np_acts-logits-general · gemini-2.0-flash

    credit and criminal background

    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
    ValueStyle
    -0.72
    WriteAttribute
    -0.61
     ब्रेकडाउन
    -0.60
    itinéraire
    -0.58
    DockStyle
    -0.58
     CountDown
    -0.55
    EndTag
    -0.55
    Chham
    -0.54
     bitumen
    -0.54
    stylesheet
    -0.53
    POSITIVE LOGITS
     background
    1.03
     credit
    0.94
     criminal
    0.93
     Background
    0.89
    background
    0.85
     Credit
    0.84
     antecedentes
    0.84
    credit
    0.81
     bakgrund
    0.80
    criminal
    0.79
    Activations Density 0.339%

    No Known Activations