© 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. 40-GEMMASCOPE-RES-16K
    6. 1440
    Prev
    Next
    INDEX
    Explanations

    references to purchasing products online

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.59
     متعلقه
    -0.38
     ...
    -0.37
    principalTable
    -0.35
     \&
    -0.33
    Cyfarwyddwr
    -0.33
     дописавши
    -0.32
    ...
    -0.32
     المعيارى
    -0.32
    “...
    -0.31
    POSITIVE LOGITS
     cheap
    1.46
     http
    1.39
     Cheap
    1.32
    cheap
    1.31
     cheapest
    1.30
     buy
    1.27
    Cheap
    1.26
     viagra
    1.23
     generic
    1.23
     https
    1.20
    Activations Density 0.264%

    No Known Activations