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. 6-GEMMASCOPE-RES-16K
    6. 6150
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and engineering products and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -1.06
     <=",
    -1.03
     HasFactory
    -1.02
    EndContext
    -0.95
    sizeCache
    -0.87
     שוליים
    -0.86
    tvguidetime
    -0.84
     للاسماء
    -0.83
    StoryboardSegue
    -0.82
    AxisAlignment
    -0.81
    POSITIVE LOGITS
    .
    0.57
    ,
    0.50
    про
    0.43
    뿐
    0.43
    <eos>
    0.42
    ()].
    0.41
     ]
    0.40
     products
    0.39
    –
    0.38
    ;
    0.38
    Activations Density 0.533%

    No Known Activations