© 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. 37-GEMMASCOPE-RES-16K
    6. 4237
    Prev
    Next
    INDEX
    Explanations

    references to challenges and the act of overcoming or facing adversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsPostBack
    -0.48
     paramString
    -0.42
    PRIOR
    -0.40
     Prior
    -0.40
     lags
    -0.40
    Prior
    -0.40
    pherals
    -0.39
     estekak
    -0.39
     IAAF
    -0.38
    Παραπομπές
    -0.38
    POSITIVE LOGITS
     devant
    2.14
     davanti
    1.86
     delante
    1.77
     أمام
    1.75
     diante
    1.74
     frente
    1.72
     framför
    1.65
     front
    1.55
     перед
    1.53
     hadapan
    1.38
    Activations Density 0.493%

    No Known Activations