© 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. 21-GEMMASCOPE-RES-16K
    6. 1737
    Prev
    Next
    INDEX
    Explanations

    technical terms and error messages related to file and directory management in computing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.94
    HomeAsUpEnabled
    -0.86
    EndContext
    -0.84
    apunov
    -0.83
    #+#
    -0.83
     religieuses
    -0.80
    انيف
    -0.80
    SourceChecksum
    -0.79
     télévisée
    -0.77
    GRAFIA
    -0.77
    POSITIVE LOGITS
     des
    0.51
    ,
    0.45
     und
    0.43
     im
    0.43
     importância
    0.41
     vom
    0.41
    vi
    0.41
     mit
    0.39
     bei
    0.39
     zur
    0.38
    Activations Density 0.029%

    No Known Activations