© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 793
    Prev
    Next
    INDEX
    Explanations

    terms related to standalone products or operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1120
    +0.08
    0.2%
    1452
    +0.07
    0.2%
    1218
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.02
    1120
    +0.07
    0.05
    1363
    +0.07
    0.04
    Negative Logits
    <bos>
    -0.71
     like
    -0.58
     di
    -0.58
    Namara
    -0.58
    קל
    -0.57
    ехали
    -0.56
     اند
    -0.56
     conduct
    -0.55
     att
    -0.55
     ди
    -0.55
    POSITIVE LOGITS
     effe
    1.99
     fta
    1.96
     „,
    1.93
     aen
    1.92
     squa
    1.92
     sovere
    1.89
     nece
    1.86
     ftu
    1.86
     fto
    1.83
     fte
    1.83
    Activations Density 0.338%

    No Known Activations