© 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. 23-GEMMASCOPE-RES-16K
    6. 5912
    Prev
    Next
    INDEX
    Explanations

    data and numerical values related to scientific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }.
    -0.64
    <sup>
    -0.64
    }}.
    -0.63
    <eos>
    -0.58
    </sub>
    -0.58
    )}.
    -0.57
    ).
    -0.54
    �
    -0.53
    …。
    -0.51
    <code>
    -0.50
    POSITIVE LOGITS
     \%$
    0.97
     يتيمه
    0.93
     \&
    0.93
     \%
    0.90
     referrerpolicy
    0.86
     \
    0.85
     ?$
    0.85
     \#
    0.85
     الدولى
    0.83
     \$
    0.82
    Activations Density 0.143%

    No Known Activations