© 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. 20-GEMMASCOPE-RES-16K
    6. 10029
    Prev
    Next
    INDEX
    Explanations

    negations or conditions related to the presence or absence of instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pleaſure
    -0.56
     itſelf
    -0.52
     ſtate
    -0.48
     houſe
    -0.47
    StoryboardSegue
    -0.47
    quelles
    -0.46
     sphere
    -0.46
     ſtre
    -0.44
     Sphere
    -0.44
     canst
    -0.44
    POSITIVE LOGITS
     (!
    1.02
    (!__
    0.97
    (!
    0.94
     (!_
    0.76
     (!$
    0.73
    (!$
    0.73
    IsContent
    0.72
    (!_
    0.69
     ((!
    0.69
    (!(
    0.63
    Activations Density 0.040%

    No Known Activations