© 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. 14751
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions or roles in a context

    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
    PyTuple
    -0.43
    Hentet
    -0.41
     zoude
    -0.40
    évaluateur
    -0.40
     pério
    -0.39
    lotl
    -0.38
     virkelig
    -0.37
     Autorizaciones
    -0.36
    versy
    -0.36
     Exacts
    -0.36
    POSITIVE LOGITS
     itself
    0.54
     FURTHER
    0.51
     then
    0.49
     further
    0.47
     herself
    0.47
     AttributeSet
    0.47
     далее
    0.45
     wiederum
    0.44
     themselves
    0.44
    itself
    0.43
    Activations Density 1.231%

    No Known Activations