© 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. 4981
    Prev
    Next
    INDEX
    Explanations

    elements of legal terminology and case references

    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
    bootstrapcdn
    -0.55
     gynhyrchwyd
    -0.53
     wireType
    -0.52
     autorytatywna
    -0.48
    يميديا
    -0.45
    燐
    -0.41
    #![
    -0.41
    DllImport
    -0.39
    OpenHelper
    -0.39
     nargin
    -0.38
    POSITIVE LOGITS
     ab
    2.59
     Ab
    2.52
    Ab
    2.38
     Abs
    2.16
     аб
    2.11
     Аб
    2.06
    ab
    2.02
    Аб
    2.02
     AB
    2.02
     abs
    1.98
    Activations Density 1.012%

    No Known Activations