© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 301
    Prev
    Next
    INDEX
    Explanations

    terms related to mountainous regions and geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.15
    0.7%
    1565
    +0.12
    0.5%
    30
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.06
    1798
    +0.12
    0.05
    1013
    +0.12
    0.05
    Negative Logits
    <bos>
    -1.62
     &___
    -0.66
     "..\..\..\
    -0.63
     Référence
    -0.54
     Dostupné
    -0.54
    ത്ത
    -0.53
     nonatomic
    -0.53
     assiste
    -0.52
    ₦
    -0.52
     gynhyrchwyd
    -0.52
    POSITIVE LOGITS
     ftu
    1.43
     ftre
    1.42
     thut
    1.42
     unwarran
    1.36
     reft
    1.35
     fays
    1.32
     ecru
    1.30
     malheureux
    1.30
     insensible
    1.29
     fta
    1.29
    Activations Density 0.291%

    No Known Activations