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. 10626
    Prev
    Next
    INDEX
    Explanations

    keywords related to data structures and mappings

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

    Code related to HashMap or mutable maps

    np_acts-logits-general · gemini-2.0-flash

    hash map and dictionary

    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
    Newswire
    -0.50
    Gambas
    -0.45
    nativeElement
    -0.44
    andes
    -0.43
    rigger
    -0.43
    borg
    -0.42
     [].
    -0.41
    瑕
    -0.41
    rictions
    -0.41
    psis
    -0.41
    POSITIVE LOGITS
     hash
    1.11
     HashMap
    1.10
    Map
    1.09
     map
    1.08
     Map
    1.07
     Hash
    1.06
    HashMap
    1.06
     dictionary
    1.06
     Dictionary
    1.02
    hash
    1.02
    Activations Density 0.443%

    No Known Activations