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. 25-GEMMASCOPE-RES-16K
    6. 3785
    Prev
    Next
    INDEX
    Explanations

    instances of whitespace or separations between words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.61
    học
    -0.53
    ьаж
    -0.53
    */].
    -0.53
    InstanceState
    -0.51
     chụp
    -0.50
    źródło
    -0.50
    tôi
    -0.50
    ^(@)
    -0.49
    })->
    -0.49
    POSITIVE LOGITS
    expandindo
    0.63
     thirty
    0.63
     eighteen
    0.61
    twelve
    0.60
     fifty
    0.59
     twelve
    0.59
    twenty
    0.58
     forty
    0.58
     twenty
    0.58
     seventeen
    0.58
    Activations Density 0.445%

    No Known Activations