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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7971
    Prev
    Next
    INDEX
    Explanations

    terms related to software issues and failures

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

    Issues or problems

    np_acts-logits-general · gemini-2.0-flash

    not working properly

    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
    IndentedString
    -0.77
     autorytatywna
    -0.73
     indestru
    -0.70
    ContentAsync
    -0.66
    LookAnd
    -0.64
    })));
    -0.64
     onlyOwner
    -0.61
    awtextra
    -0.59
    irements
    -0.58
     GenerationType
    -0.58
    POSITIVE LOGITS
     anymore
    1.18
     properly
    1.16
     nor
    1.11
     due
    0.99
    properly
    0.88
     adequately
    0.86
     despite
    0.85
     :(
    0.84
    due
    0.80
    而是
    0.80
    Activations Density 0.449%

    No Known Activations