© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6910
    Prev
    Next
    INDEX
    Explanations

    references to female characters or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -0.69
    umu
    -0.59
    诸多
    -0.59
    cek
    -0.58
    mba
    -0.58
    top
    -0.58
    autre
    -0.57
    getError
    -0.56
     top
    -0.56
    ual
    -0.56
    POSITIVE LOGITS
     she
    1.72
    she
    1.63
    She
    1.54
     She
    1.39
     shes
    1.35
     SHE
    1.26
    SHE
    1.24
     herself
    1.06
     которая
    1.05
    Datuak
    1.01
    Activations Density 0.064%

    No Known Activations