Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10575
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the prefix "ab" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    -0.70
    CreateModel
    -0.67
     osi
    -0.67
    Oni
    -0.64
    Configurer
    -0.64
    }^{*}(
    -0.63
    ConstraintLayout
    -0.62
     MCM
    -0.62
     gril
    -0.60
     >(
    -0.60
    POSITIVE LOGITS
     ab
    2.87
     Ab
    2.79
    Ab
    2.49
     AB
    2.29
    ab
    2.25
    AB
    1.90
     Аб
    1.56
     abzu
    1.54
     Abby
    1.43
     ablation
    1.40
    Activations Density 0.077%

    No Known Activations