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. 24-GEMMASCOPE-RES-16K
    6. 2317
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations and institutions

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

    Prepositions and abbreviations before capitalized words

    np_acts-logits-general · gemini-2.0-flash

    names following HCC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.60
     виправивши
    -0.55
     Frontera
    -0.54
    chloro
    -0.54
     Administrativna
    -0.53
    oredCriteria
    -0.51
    ész
    -0.49
     ←
    -0.49
     ब्रेकडाउन
    -0.49
     EClass
    -0.48
    POSITIVE LOGITS
    DotNetBar
    0.60
     <<<<<<<<<<<<<<
    0.59
     }}"></
    0.57
    govina
    0.57
    istoitu
    0.55
    ]));
    
    0.54
     magasiner
    0.53
    bys
    0.52
    ricanes
    0.52
    ")));
    
    0.52
    Activations Density 0.106%

    No Known Activations