© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7984
    Prev
    Next
    INDEX
    Explanations

    phrases related to job recruitment and NHS services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    倒
    -0.37
     compétence
    -0.35
     CanadaChoose
    -0.35
     Kompetenz
    -0.35
    sonaro
    -0.35
     Constitucional
    -0.32
    cedula
    -0.32
     chimique
    -0.31
    stateParams
    -0.30
     OMITBAD
    -0.30
    POSITIVE LOGITS
     Bristol
    1.02
     Leeds
    0.99
     Manchester
    0.98
     Liverpool
    0.96
     Birmingham
    0.93
     Sheffield
    0.93
     Nottingham
    0.93
     Leicester
    0.92
     Cardiff
    0.90
     Newcastle
    0.88
    Activations Density 0.331%

    No Known Activations