© 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. 1-GEMMASCOPE-RES-16K
    11. 9936
    Prev
    Next
    INDEX
    Explanations

    instances of data formatting and syntax structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \}
    -0.59
    }
    -0.54
    isfile
    -0.54
    hip
    -0.53
     Leer
    -0.53
    \%
    -0.47
     \&
    -0.46
    اژ
    -0.46
     \%
    -0.45
    acana
    -0.45
    POSITIVE LOGITS
    </h1>
    1.09
    </h2>
    1.06
    __":
    1.04
    </h3>
    0.98
    __":
    0.94
    __':
    0.90
    BeginContext
    0.86
    </h5>
    0.86
    </h4>
    0.85
     resourceCulture
    0.84
    Activations Density 0.126%

    No Known Activations