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. 21-GEMMASCOPE-RES-16K
    6. 1974
    Prev
    Next
    INDEX
    Explanations

    HTML classes and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.66
    Geplaatst
    -0.65
    :✨
    -0.59
    autoIncrement
    -0.59
    CppMethod
    -0.56
     bool
    -0.50
    Brainz
    -0.50
     Bland
    -0.49
    BROAD
    -0.49
     FALSE
    -0.49
    POSITIVE LOGITS
    Datuak
    0.69
    ValueStyle
    0.66
    ########.
    0.64
    '}>
    0.61
    AppCompatTheme
    0.58
    __*/
    0.57
    '>{
    0.57
    ']:
    0.56
    ."]
    0.55
    »).
    0.55
    Activations Density 0.020%

    No Known Activations