Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73491
    Prev
    Next
    INDEX
    Explanations

    assertions and checks for null values in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.68
     CURLOPT
    -0.54
     دیکھیے
    -0.53
    +#+
    -0.51
     שוליים
    -0.49
    ########.
    -0.48
     
    -0.47
    outSlope
    -0.47
    enumii
    -0.46
    TypedDataSet
    -0.45
    POSITIVE LOGITS
    Preconditions
    0.43
    UnsafeEnabled
    0.42
    modb
    0.40
    JSONException
    0.40
    DebuggerStep
    0.39
     desem
    0.39
     neceff
    0.38
     neither
    0.38
    Clint
    0.38
    قایناقلار
    0.38
    Activations Density 0.010%

    No Known Activations