© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5841
    Prev
    Next
    INDEX
    Explanations

    mentions of personal relationships with an emphasis on individual experiences and community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    fjspx
    -0.63
    pett
    -0.46
    featureID
    -0.44
    Билгалдахарш
    -0.44
     defaultstate
    -0.44
     étr
    -0.43
     ſche
    -0.43
    åringen
    -0.43
     MEASUREMENT
    -0.43
    peq
    -0.42
    POSITIVE LOGITS
     me
    0.49
    instancetype
    0.47
     us
    0.43
     myself
    0.42
     undersigned
    0.41
    ⟬
    0.40
     мной
    0.38
     ourselves
    0.37
    myself
    0.37
     disambiguazione
    0.35
    Activations Density 0.484%

    No Known Activations