© 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. 25-GEMMASCOPE-RES-16K
    6. 5368
    Prev
    Next
    INDEX
    Explanations

    instances of possessive contractions and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.56
    السكان
    -0.54
    adpleegd
    -0.54
    Czytaj
    -0.54
    webElementGuid
    -0.53
    AILABLE
    -0.53
    føring
    -0.53
    HostException
    -0.52
    ERSHIP
    -0.51
    ữu
    -0.51
    POSITIVE LOGITS
    ll
    1.59
    s
    1.33
    d
    1.09
    lll
    0.72
     تانيه
    0.70
     ll
    0.70
    llll
    0.69
    lln
    0.68
    ofern
    0.66
    Ll
    0.66
    Activations Density 0.163%

    No Known Activations