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. 5-GEMMASCOPE-RES-16K
    6. 3520
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in data that indicate correct alignment or fit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.67
     naselje
    -0.49
    — 
    -0.47
     profusely
    -0.43
     OnEnable
    -0.43
    iyor
    -0.43
     Richter
    -0.42
    اث
    -0.42
     Effect
    -0.42
    ktan
    -0.42
    POSITIVE LOGITS
     matching
    1.23
     Matching
    1.16
     matches
    1.14
     matched
    1.10
    matching
    1.09
     MATCH
    1.08
    Matching
    1.06
     match
    1.06
     Matches
    1.04
    matched
    1.01
    Activations Density 0.365%

    No Known Activations