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. 24-GEMMASCOPE-RES-16K
    6. 14148
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their manipulations

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

    Code delimiters and punctuation

    np_acts-logits-general · gemini-2.0-flash

    numerals and punctuation

    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
     للمعارف
    -0.88
    SourceChecksum
    -0.86
    ########.
    -0.82
    afficheront
    -0.79
    Hentet
    -0.78
    APORE
    -0.78
     الحره
    -0.77
    ритори
    -0.77
    发表于
    -0.76
    ioutil
    -0.75
    POSITIVE LOGITS
     Theſe
    0.55
     Monfieur
    0.52
     auroit
    0.47
     étoit
    0.45
     feroit
    0.44
     myſelf
    0.44
     pouvoit
    0.43
    <bos>
    0.41
     mourut
    0.38
     himſelf
    0.38
    Activations Density 0.300%

    No Known Activations