© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3553
    Prev
    Next
    INDEX
    Explanations

    translations of the words "lemon" and "mint" in Arabic and Hebrew, respectively, alongside related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    605
    +0.15
    0.5%
    1871
    +0.14
    0.4%
    1385
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1830
    +0.15
    0.02
    1343
    +0.14
    0.02
    1559
    +0.14
    0.01
    Negative Logits
    ,
    -0.95
    .
    -0.93
    ;
    -0.91
    ↵↵
    -0.85
    ...
    -0.85
    、
    -0.84
     (
    -0.84
    ↵
    -0.83
    '
    -0.83
    </em>
    -0.83
    POSITIVE LOGITS
     milano
    2.22
     bayern
    2.22
     bourgeo
    2.21
     valencia
    2.18
     dises
    2.15
     alberto
    2.13
     frankfurt
    2.13
     napoli
    2.12
     paillettes
    2.11
     pessi
    2.10
    Activations Density 0.041%

    No Known Activations