Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 48
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.91
    ✨:
    -0.90
     GNA
    -0.86
    دانشنامهٔ
    -0.82
    PREDICT
    -0.81
    ]}$
    -0.79
    intellij
    -0.78
     spalle
    -0.78
    bleed
    -0.77
    }}/>
    -0.77
    POSITIVE LOGITS
    ----------------
    1.95
    ---------------
    1.38
    --------------
    1.22
    ------------
    1.20
    -------------
    1.13
    --------
    1.12
    -----------
    1.09
    ------
    1.04
    ---------
    1.04
    -------
    1.02
    Activations Density 0.166%

    No Known Activations