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. 15469
    Prev
    Next
    INDEX
    Explanations

    academic qualifications and degrees, particularly in nursing and administration

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

    Followed by a field of study

    np_acts-logits-general · gemini-2.0-flash

    degrees, subjects, or fields of study

    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
    coloured
    -0.73
    tanleria
    -0.73
     honour
    -0.72
     PROGRAMME
    -0.70
     honoured
    -0.69
    tvguidetime
    -0.69
     متعلقه
    -0.67
    programme
    -0.66
    StoryboardSegue
    -0.64
    Programme
    -0.64
    POSITIVE LOGITS
    #+#
    0.56
     dátum
    0.50
     concent
    0.49
     concentration
    0.44
     concentrations
    0.43
    ISupport
    0.43
     gelieb
    0.42
    __*/
    0.41
     criminal
    0.41
    показания
    0.41
    Activations Density 0.114%

    No Known Activations