© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2830
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender-based differences and family planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Were/are" followed by probability words

    np_acts-logits-general · gemini-2.0-flash

    likelymoreless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haut
    -0.43
    LO
    -0.41
     straps
    -0.40
    ichi
    -0.40
     lub
    -0.40
    ue
    -0.39
    var
    -0.38
    alt
    -0.38
     खे
    -0.38
     j
    -0.38
    POSITIVE LOGITS
     likelihood
    1.22
     likely
    1.21
     cenderung
    1.04
    Likely
    1.03
     Likely
    1.03
    likely
    1.02
     tendency
    1.01
     Chances
    1.00
     Likelihood
    1.00
     tended
    0.98
    Activations Density 0.504%

    No Known Activations