© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1707
    Prev
    Next
    INDEX
    Explanations

    blocks of text that serve as documentation or comments

    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
    </b>
    -0.72
    ed
    -0.65
    a
    -0.64
    eb
    -0.57
    o
    -0.56
     ± 
    -0.55
    <b>
    -0.55
    いけ
    -0.54
    RICAL
    -0.53
    ev
    -0.53
    POSITIVE LOGITS
    """
    2.40
     """
    2.14
    ."""
    1.96
    """
    1.90
     """
    1.64
    ("""
    1.58
    """"
    1.48
    '''
    1.44
     ***!
    1.29
    """)
    1.27
    Activations Density 0.094%

    No Known Activations