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. 11330
    Prev
    Next
    INDEX
    Explanations

    the phrase "no matter" and 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
     „
    -0.55
     «
    -0.50
     “
    -0.49
     "../../../
    -0.48
     publics
    -0.46
     tids
    -0.45
     Navarra
    -0.45
     אלה
    -0.45
     недавно
    -0.44
    paris
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    1.06
    ostante
    1.03
    Wherever
    0.98
     Wherever
    0.97
    InjectAttribute
    0.95
    <?
    0.94
    SizeF
    0.93
    osoever
    0.92
     wherever
    0.92
    +#+#
    0.92
    Activations Density 0.103%

    No Known Activations