© 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. 22-GEMMASCOPE-RES-16K
    6. 13308
    Prev
    Next
    INDEX
    Explanations

    references to ecological and biological concepts related to species and their adaptations

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

    Prepositions that begin a clause or sentence

    np_acts-logits-general · gemini-2.0-flash

    In addition

    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
     Efq
    -1.44
    principalColumn
    -1.20
     насељу
    -1.18
    featureID
    -1.15
    ſelf
    -1.15
     Anſ
    -1.15
    DockStyle
    -1.15
    UrlResolution
    -1.13
     whoſe
    -1.13
     myſelf
    -1.13
    POSITIVE LOGITS
     another
    0.93
     As
    0.91
     Another
    0.89
     
    0.83
    ↵↵
    0.81
     In
    0.77
    Another
    0.75
     Before
    0.75
    ↵
    0.75
     So
    0.74
    Activations Density 0.501%

    No Known Activations