© 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. 18-GEMMASCOPE-RES-16K
    6. 6817
    Prev
    Next
    INDEX
    Explanations

    elements related to design and branding in communication

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

    Brand or corporate image/identity

    np_acts-logits-general · gemini-2.0-flash

    brand image and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -0.66
    batore
    -0.57
     للمعارف
    -0.56
     mại
    -0.56
    مقاله
    -0.55
    Demografie
    -0.51
    pausal
    -0.51
    LastError
    -0.50
    पया
    -0.49
    tonode
    -0.49
    POSITIVE LOGITS
     logo
    1.20
     branding
    1.10
     corporate
    1.09
     brand
    1.07
    brand
    1.05
    logo
    0.98
     Logo
    0.94
    Brand
    0.93
     Brand
    0.92
    corporate
    0.91
    Activations Density 0.171%

    No Known Activations