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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6401
    Prev
    Next
    INDEX
    Explanations

    phrases that describe challenges or difficulties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.57
    UserScript
    -0.55
    exitRule
    -0.55
     Audiodateien
    -0.53
    astify
    -0.53
     &___
    -0.53
    twimg
    -0.49
    posedge
    -0.48
    tdessen
    -0.48
     muzzle
    -0.48
    POSITIVE LOGITS
    difficult
    1.03
    Difficult
    1.02
     Difficult
    1.02
     difficult
    0.97
    Difficulty
    0.85
     Difficulty
    0.84
     diffic
    0.84
    difficulty
    0.81
     difficile
    0.79
     moeilijk
    0.76
    Activations Density 0.152%

    No Known Activations