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. 12930
    Prev
    Next
    INDEX
    Explanations

    keywords associated with outcomes and impacts, particularly related to ability and obstacles

    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
    ندگی
    -0.63
    thâu
    -0.59
    yntaxException
    -0.57
    preuve
    -0.54
    nastics
    -0.54
    elfde
    -0.53
    AndEndTag
    -0.53
    UCKY
    -0.53
    TintMode
    -0.53
    testens
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.61
    \#:
    0.52
    LookAnd
    0.51
     inmediato
    0.49
     Ene
    0.49
    '},
    
    0.49
    """
    
    0.49
    enumi
    0.48
    )]:
    0.48
    '''
    
    0.48
    Activations Density 0.565%

    No Known Activations