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. 22-GEMMASCOPE-RES-16K
    6. 8058
    Prev
    Next
    INDEX
    Explanations

    references to accountability and consequences related to actions

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

    Followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    pronoun + auxiliary verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.71
    (!__
    -0.71
    GroupLayout
    -0.70
    GEBURTSDATUM
    -0.61
    ostante
    -0.58
    @[+][
    -0.57
     betweenstory
    -0.57
     iprot
    -0.56
     CURIAM
    -0.55
    TagNumber
    -0.55
    POSITIVE LOGITS
     automatically
    1.07
     automaticamente
    1.03
     automáticamente
    0.99
     automatiquement
    0.94
     автоматически
    0.90
     automatisch
    0.88
    automatically
    0.88
     indirectly
    0.83
    ówczas
    0.80
     chances
    0.78
    Activations Density 0.391%

    No Known Activations