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. 10357
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and arguments

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

    after commas or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    legal arguments and requests

    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
    setTypeface
    -0.62
    AxisAlignment
    -0.52
    ceği
    -0.51
    OrNil
    -0.51
     '\\;'
    -0.49
     demografica
    -0.49
     برانيه
    -0.49
    ایج
    -0.48
    ((*
    -0.48
    bootstrapcdn
    -0.48
    POSITIVE LOGITS
     saying
    2.61
    saying
    2.15
     stating
    2.07
     noting
    2.00
    Saying
    1.87
     Saying
    1.86
     citing
    1.84
     diciendo
    1.67
     sayin
    1.64
     mentioning
    1.56
    Activations Density 0.421%

    No Known Activations